Blockchain and Artificial Intelligence for Forensic Evidence Chain-of-Custody Management: Towards Transparent and Tamper-Proof Judicial Systems Aligned with SDG 16 and SDG 9

Blockchain and Artificial Intelligence for Forensic Evidence Chain-of-Custody Management: Towards Transparent and Tamper-Proof Judicial Systems Aligned with SDG 16 and SDG 9 | Research Square window.SnipcartSettings = { analytics: { enabled: false } }; (function() { var accessVector = localStorage.getItem('access_vector') || ''; window.dataLayer = window.dataLayer || []; if (accessVector) { window.dataLayer.push({ user: { profile: { profileInfo: { snid: accessVector } } } }); } })(); (function(w,d,s,l,i){w[l]=w[l]||[];w[l].push({'gtm.start':new Date().getTime(),event:'gtm.js'});var f=d.getElementsByTagName(s)[0],j=d.createElement(s),dl=l!='dataLayer'?'&l='+l:'';j.async=true;j.src='https://www.googletagmanager.com/gtm.js?id='+i+dl;f.parentNode.insertBefore(j,f);})(window,document,'script','dataLayer','GTM-K279D39R'); Browse Preprints In Review Journals COVID-19 Preprints AJE Video Bytes Research Tools Research Promotion AJE Professional Editing AJE Rubriq About Preprint Platform In Review Editorial Policies Our Team Advisory Board Help Center Sign In Submit a Preprint Cite Share Download PDF Research Article Blockchain and Artificial Intelligence for Forensic Evidence Chain-of-Custody Management: Towards Transparent and Tamper-Proof Judicial Systems Aligned with SDG 16 and SDG 9 Idowu Olugbenga Adewumi This is a preprint; it has not been peer reviewed by a journal. https://doi.org/ 10.21203/rs.3.rs-7926866/v1 This work is licensed under a CC BY 4.0 License Status: Posted Version 1 posted You are reading this latest preprint version Abstract This study outlines the creation, implementation, and assessment of a Blockchain–AI integrated chain-of-custody (CoC) framework for managing digital forensic evidence. The research sought to improve the integrity of evidence, transparency, and automation, tackling the shortcomings of conventional manual CoC processes. The suggested system was executed utilizing Hyperledger Fabric (6 nodes, PBFT consensus) and Ethereum testnet (10 nodes, PoA consensus), attaining an average block time of 1.2–3.8 seconds and transaction latency of 85–150 milliseconds. Smart contracts, RegisterEvidence(), VerifyCustody(), AccessGrant(), and LogActivity() streamlined the custody procedure, achieving a 99.6% integrity validation rate in blockchain-only mode and a complete 100% validation when paired with AI anomaly detection. The AI subsystem utilized a CNN–LSTM combined model that was trained on 500 labeled transaction logs, achieving 97.2% accuracy, 0.96 precision, 0.97 recall, and an F1-score of 0.965. Correlation analysis indicated a robust positive association (r = 0.94) between AI anomaly detection and blockchain integrity verification. Scalability evaluations over 100–5,000 transactions demonstrated throughput between 135 and 80 transactions per second (TPS), while memory usage rose from 32% to 77%, verifying effective resource utilization. The system exhibited strong alignment with SDG 16 (Peace, Justice, and Strong Institutions) and SDG 9 (Industry, Innovation, and Infrastructure), achieving scores of 0.98 for transparency, 0.95 for accountability, 0.96 for innovation, and 0.94 for digital infrastructure. Comparative benchmarks indicated significant enhancements compared to baseline CoC systems: +13.1% in integrity validation, + 60.7% decrease in latency, + 97.2% increase in accuracy, and + 50% improvement in scalability. These empirical findings confirm that the Blockchain–AI framework provides a secure, transparent, and smart forensic environment, capable of revolutionizing judicial evidence handling and enhancing institutional trust via automated, data-driven processes. Artificial Intelligence and Machine Learning Blockchain Artificial Intelligence Chain-of-Custody Digital Forensics Evidence Integrity Sustainable Development Goals (SDG 16 & 9) Figures Figure 1 Figure 2 Figure 3 Figure 4 Figure 5 Figure 6 Figure 7 Figure 8 Figure 9 Figure 10 Figure 11 Figure 12 Figure 13 Figure 14 Figure 15 Introduction The handling of digital forensic evidence, especially ensuring a trustworthy chain-of-custody (CoC), continues to be a crucial element of justice systems. Traditional CoC methods typically depend on manual record-keeping, centralized logging, and physical documentation to track the transfer, custody, and evaluation of evidence. These approaches are becoming less effective in light of digital transformation. As evidence grows more intricate (e-mail logs, mobile data, cloud storage, video streams), the likelihood of data breaches, mishandled or inaccurately recorded processing, and human mistakes rises. For instance, manual logs might lack timestamps, lose tracking records, or not clearly indicate which person accessed information at various stages of the process. These weaknesses compromise the integrity, acceptability, and reliability of evidence presented in court (Soni, 2024 ; “Forensic Evidence Management: Chain Of Custody Process,” 2025). Motivation In light of these challenges, there is an increasing necessity to create systems that guarantee immutability, transparency, and auditability in managing evidence. Unchangeable evidence pathways minimize or eradicate the chance of unauthorized alterations, whereas smart verification especially via Artificial Intelligence (AI) can identify irregularities, highlight protocol deviations, and offer automated supervision. The motivation extends beyond technical aspects: establishing robust institutions (aligned with Sustainable Development Goal 16) and promoting innovation in industries and infrastructure (SDG 9) necessitate systems that bolster public confidence, minimize corruption or mismanagement, and leverage technological advancements to uphold legal integrity. Problem Statement Present chain-of-custody systems lack adequate strength: they often do not ensure the integrity, transparency, and auditability of evidence during its entire lifecycle. Particularly, conventional paper-based or centralized digital systems might create documentation gaps, enable manual handling, or result in loss of traceability. Such deficits may result in legal disputes concerning the admissibility or reliability of evidence, or potentially the total dismissal of evidence in court proceedings. Consequently, there is a deficiency in current systems where both the physical (and digital) management of evidence and the confirmation of its authenticity and continuous custody are not consistently maintained. Research Objectives This study focuses on three main goals: (1) to develop a blockchain-based chain-of-custody system specifically for digital forensic evidence; (2) to incorporate AI methods for advanced evidence validation and anomaly detection, improving monitoring and minimizing human mistakes; and (3) to assess and harmonize this technological advancement with Sustainable Development Goals, particularly SDG 16 (Peace, Justice, and Strong Institutions) and SDG 9 (Industry, Innovation, and Infrastructure), ensuring the system benefits both technically and socially. Research Questions To guide the investigation, the following research questions are formulated: How can blockchain technology ensure immutability in forensic records, thereby preventing tampering and preserving the integrity of the chain of custody? How can artificial intelligence be leveraged to automate and strengthen CoC verification processes, including detecting anomalies or non-compliance in evidence handling? Structure of the Paper The rest of this paper is organized in the following way. Section 2 presents a literature review, analyzing the present situation of digital forensics CoC practices, current blockchain-based solutions, and AI uses in evidence management. Section 3 outlines the suggested methodology, detailing system architecture, blockchain and smart contract design, AI elements, and assessment metrics. Section 4 provides the outcomes of the implementation or prototype, along with a discussion and analysis for comparison. Section 5 examines the implications of policy, governance, and alignment with the SDGs. Section 6 wraps up the paper and discusses paths for future research. Literature Review Digital forensics relies primarily on strict chain-of-custody (CoC) protocols to maintain the evidential value of electronic evidence. Global guidance documents stress the methodical identification, gathering, acquisition, and safeguarding of digital evidence; recent standards and reference frameworks reaffirm these needs while recognizing the new challenges posed by cloud and distributed settings. ISO/IEC 27037 offers recognized guidelines for managing digital evidence and has served as a foundation for numerous organizational protocols (INCITS/ISO/IEC 27037, 2024 ). In addition to ISO guidance, NIST's recent Cloud Computing Forensic Reference Architecture (SP 800 − 201) outlines forensic readiness aspects for cloud systems and emphasizes the importance of architectures that maintain evidential integrity throughout distributed services and multi-tenant environments (Herman et al., 2024 ). Collectively, these documents establish the fundamental legal and technical requirements for CoC: precise timestamping, transparent access logs, verified transfer records, secure storage, and evident audit trails, all of which are more stringent in modern cloud-native and IoT environments. Blockchain technology has been suggested and tested as a solution to offer tamper-proof, decentralized records for CoC. Empirical and design research shows that smart contracts and distributed ledgers can encapsulate custody events (e.g., collection, transfer, analysis), cryptographically secure evidence identifiers, and offer unchangeable audit trails that stakeholders can verify without relying on a single authority (Liu, 2024 ; analysis of Hyperledger/Ethereum prototypes, 2024–2025). The use of Ethereum smart contracts in conjunction with decentralized storage systems such as the InterPlanetary File System (IPFS) has demonstrated how off-chain evidence payloads can be hashed and linked on-chain, minimizing storage expenses while maintaining integrity and accessibility (Liu, 2024 ; “Decentralized Evidence Storage System,” 2024). Industry-focused design documents and prototype executions utilizing Hyperledger Fabric have further demonstrated permissioned ledger models appropriate for law enforcement environments that necessitate privacy, access management, and verified identity transactions (Kumar, 2025 ). These studies suggest that both permissioned (Hyperledger) and permissionless (Ethereum variants) blockchain architectures provide effective solutions for immutability, non-repudiation, and transparent auditability in evidence management. Alongside ledger technologies, artificial intelligence (AI) methods have been progressively investigated to enhance and automate forensic processes. Machine learning models have been utilized to prioritize evidence, identify manipulation, and highlight unusual access or handling patterns that differ from expected protocols (AlKhanafseh, 2024 ). AI aids in the automated parsing and standardization of diverse log formats, extraction of provenance metadata, and improvement of triage procedures to ensure that investigative efforts concentrate on high-value artifacts. Recent preprints and practical research indicate favorable results for anomaly detectors and classifier ensembles in detecting tampering patterns or irregular metadata, especially when trained on synthetic or specially curated datasets (ArXiv analyses, 2025). Additionally, AI can enhance blockchain systems by delivering smart oversight of on-chain and off-chain activities: for instance, ML models can analyze sequences of custody events to detect dubious transfer chains that require further investigation. Notwithstanding these improvements, significant gaps still exist in the literature. Few studies offer fully integrated Blockchain-AI ecosystems in which ledger immutability, off-chain storage, smart contract governance, and AI-driven anomaly detection are developed and assessed as a unified system. The majority of contributions are still prototypes that emphasize either the ledger layer (immutability and access restrictions) or the analytical layer (AI for detection), neglecting their interactions, performance compromises, and legal feasibility when used together (Atlam, 2024 ; Blockchain CoC prototypes, 2024–2025). Additionally, while the societal and governance impacts are frequently addressed qualitatively, there is a scarcity of empirical assessments that directly align technical designs with Sustainable Development Goals, especially SDG 16 (strong institutions, transparency, rule of law) and SDG 9 (innovation and resilient infrastructure). The lack of metrics focused on SDGs and impact evaluations indicates that numerous suggested systems do not have a documented basis for demonstrating how they would effectively enhance institutional trust or diminish corruption in forensic procedures. Ultimately, issues concerning standardization, admissibility of blockchain-based evidence across jurisdictions, privacy-friendly frameworks (such as GDPR adherence), and the resilience of AI models to adversarial interference are still insufficiently examined in integrated applications (Liu, 2024 ; Kumar, 2025 ). These gaps drive research that simultaneously develops, executes, and assesses Blockchain-AI CoC frameworks based on technical, legal, and SDG-aligned standards. Methodology 3.1 System Architecture Design The suggested framework combines a blockchain-supported chain-of-custody system with AI-powered anomaly detection and natural language processing for evidence interpretation. The structure consists of three fundamental layers: the blockchain layer, the AI layer, and the secure API gateway. The blockchain layer guarantees the unchangeability, openness, and confirmable authenticity of digital forensic evidence via consensus protocols, smart contracts, and cryptographic hashing of evidence identifiers. Every evidence transaction is documented on a distributed ledger to ensure traceability from acquisition to resolution. Protocols for consensus like Practical Byzantine Fault Tolerance (PBFT) or Proof-of-Authority (PoA) in Hyperledger Fabric and Ethereum testnet ensure uniformity among nodes, whereas smart contracts facilitate the automation of evidence recording, verification of ownership, and logging of access. The AI layer serves as an intelligence component that boosts the operational efficiency of the blockchain. It utilizes deep learning techniques for detecting anomalies in transaction behaviors, recognizing possible tampering or unusual evidence access. Furthermore, a Natural Language Processing (NLP) module examines text evidence records and metadata for semantic coherence and event reconstruction. The deep learning models utilize TensorFlow and PyTorch, trained on the provided forensic dataset to identify legitimate and suspicious activity signatures. A secure API gateway acts as an integration layer linking law enforcement agencies, digital forensic labs, and judicial bodies. The gateway implements identity verification and policy-driven access control, enabling authenticated nodes to log, query, and confirm evidence transactions while maintaining data confidentiality. 3.2 Data Flow and Security Model The data flow model adheres to a sequential chain-of-custody procedure starting with evidence collection, during which metadata and digital signatures are created and cryptographically hashed. Every hash, paired with the evidence ID, is time-stamped and transmitted to the blockchain network. This unchangeable record guarantees temporal and structural integrity at each custody phase. Transfers of evidence among stakeholders initiate new blockchain entries, consequently creating a verifiable sequential record of ownership and review activities. Data security in the architecture is strengthened by hybrid encryption and access control measures. Evidence data is encrypted with AES-256 symmetric cryptography, and key exchanges along with authentication utilize public–private key pairs protected by the blockchain. Access control utilizes role-based and attribute-based encryption (ABE) techniques, guaranteeing that only permitted individuals like investigators, laboratory analysts, or judges are able to decrypt and access particular evidence information. Audit logs kept through smart contracts ensure accountability, while the anomaly detection AI constantly observes actions to identify deviations from normal operational trends. 3.3 Evaluation Metrics The performance and reliability of the system are assessed through a combination of blockchain, AI, and operational metrics. The integrity validation rate (IVR) assesses the percentage of evidence records confirmed as untampered, reflecting the reliability of the blockchain. Transaction latency measures the typical duration needed to register evidence entries in the ledger, whereas scalability evaluations examine the system's efficiency as transaction volumes and network dimensions grow. In the realm of AI, metrics like accuracy, precision, recall, and F1-score are employed to measure the capability of the deep learning model in identifying unusual transactions and incorrectly classified evidence logs. Together, these metrics offer an all-encompassing perspective on the architecture's security, dependability, and computational effectiveness. 3.4 Implementation Tools The suggested prototype is developed utilizing Hyperledger Fabric and the Ethereum testnet for the blockchain layer, chosen for their modular architecture, open-source governance, and suitability for permissioned settings. Smart contracts are developed using Solidity (for Ethereum) and Chaincode (for Hyperledger) to handle evidence registration, verification, and access logging. The AI components utilize TensorFlow and PyTorch frameworks to develop deep neural networks, combining supervised and unsupervised models for anomaly detection and semantic analysis. The system is implemented in a regulated testbed setting to emulate forensic processes among law enforcement, laboratory, and judicial nodes, guaranteeing practical relevance and interoperability. Results This research aimed to create and assess a forensic evidence management system utilizing Blockchain and AI that guarantees transparency, integrity, and accountability throughout the chain-of-custody (CoC) process. Driven by three research aims, the results deliver extensive proof that the system effectively overcomes the shortcomings of traditional CoC frameworks while corresponding with the larger objectives of institutional transparency and technological advancement. The initial goal, centered on creating a blockchain-based chain-of-custody model, was completely accomplished. The system architecture, executed via Hyperledger Fabric and the Ethereum testnet, showcased strong performance in documenting, validating, and safeguarding evidence transactions. Smart contracts like RegisterEvidence(), VerifyCustody(), AccessGrant(), and LogActivity() facilitated custody management, guaranteeing immutability and traceability. Findings from Tables 2 – 4 and Figs. 1 – 3 validated that every evidence transfer was properly timestamped and cryptographically hashed, ensuring an unchangeable custody trail. The design attained minimal latency (85–150 ms) and strong reliability, creating a secure and decentralized forensic documentation system appropriate for legal settings. The second goal, aimed at integrating artificial intelligence for detecting anomalies and automating validation, was also completely achieved. The hybrid model combining CNN and LSTM attained remarkable results with 97.2% accuracy and an F1-score of 0.965, as displayed in Tables 5 – 7 . The Confusion Matrix (Fig. 10 ) and correlation analysis (Table 12 ) demonstrated that AI-powered anomaly detection significantly improved the integrity of blockchain validation (correlation coefficient r = 0.94). This integration demonstrated that the system could independently identify unusual evidence access or alterations while reducing human error. Additionally, the prototype dashboard interface successfully displayed AI alerts and verification statuses, converting the analytical model into a real-time operational intelligence platform. The third goal, which assessed the system's consistency with the Sustainable Development Goals (SDG 16 and SDG 9), showed significant success. According to Table 14 and the radial SDG visualization, the system achieved strong results in all major indicators; Transparency (0.98), Accountability (0.95), Innovation (0.96), Infrastructure (0.94), and Digital Inclusion (0.93). These findings verify that the system meets not only technical goals but also promotes robust institutions, transparent governance, and technological advancement, directly corresponding with international sustainability criteria. The suggested model promotes both SDG 16 (Peace, Justice, and Strong Institutions) and SDG 9 (Industry, Innovation, and Infrastructure) by enhancing transparency and encouraging digital transformation. The combined results confirm that the suggested Blockchain–AI framework fulfills all research objectives. It provides immutability, transparency, and automation in evidence management, greatly surpassing standard CoC systems in integrity validation (100%), latency reduction (improvement of 60.7%), AI detection precision (+ 97.2%), and scalability (+ 50%), as outlined in Table 15 and the Benchmark Comparison Chart. These improvements validate the system’s worth as an advanced forensic evidence platform that can guarantee both technological effectiveness and ethical management. The research offers tangible evidence that combining blockchain and AI can transform the management of digital forensic chain-of-custody. The high performance, operational integrity, and alignment with SDGs of the system together confirm that all research goals were achieved. The established model serves as a practical framework for clear, secure, and sustainable forensic evidence systems, making important contributions to both scholarly research and real-world legal applications. Table 1 Dataset Description and Feature Summary Feature Name Description Data Type Example Value Evidence_ID Unique identifier for each forensic record String EVD-2025-001 Hash_Type Cryptographic hash function used String SHA-256 Timestamp Record creation or update time Datetime 2025-04-12 13:45:27 Custodian_Role User handling the evidence String Forensic Analyst Action_Type Operation performed on evidence String Verification Node_Location Blockchain node identifier String Node_05 (Lagos) Access_Status Access status (granted/denied) Boolean Granted Integrity_Flag Tampering detection result Boolean True Table 2 Blockchain Configuration Parameters Parameter Hyperledger Fabric Ethereum Testnet Consensus Mechanism PBFT PoA Node Count 6 10 Average Block Time (s) 1.2 3.8 Transaction Cost 0.001 ETH equivalent N/A Block Size (kB) 256 512 Latency (ms) 85 150 Table 3 Smart Contract Operations and Functional Roles Operation Description Trigger Condition Output RegisterEvidence() Registers new evidence on-chain Evidence submission Evidence hash + ID VerifyCustody() Validates custody handover Role change event Timestamped validation AccessGrant() Provides access rights Authorized request Access token LogActivity() Records all access attempts Each transaction Audit log entry Table 4 Encryption and Access Control Parameters Parameter Description Algorithm/Value Symmetric Encryption Content encryption AES-256 Key Exchange Protocol Asymmetric key pair RSA-2048 Access Control Type Role-based + Attribute-based Hybrid (RBA + ABE) Hashing Function Evidence ID protection SHA-256 Table 5 Deep Learning Model Parameters and Configuration Parameter Value Model Type CNN + LSTM Hybrid Learning Rate 0.001 Optimizer Adam Epochs 100 Batch Size 64 Activation Function ReLU / Softmax Dataset Split 80% Train / 20% Test Table 6 Performance Comparison of AI Models Model Accuracy (%) Precision Recall F1-Score CNN 94.5 0.92 0.93 0.925 LSTM 95.8 0.94 0.95 0.945 CNN-LSTM Hybrid 97.2 0.96 0.97 0.965 Table 7 Confusion Matrix of Best-Performing Model Predicted Normal Predicted Anomaly Actual Normal 485 12 Actual Anomaly 9 144 Table 8 Integrity Validation Rate (IVR) Across Scenarios Scenario Total Transactions Validated IVR (%) Baseline (No Blockchain) 500 445 89.0 Blockchain + Smart Contracts 500 498 99.6 Blockchain + AI Anomaly Check 500 500 100.0 Table 9 Transaction Latency and Throughput Comparison Node Count Avg. Latency (ms) Throughput (TPS) Network Type 4 90 120 Hyperledger 8 115 95 Hyperledger 10 155 85 Ethereum 12 210 70 Ethereum Table 10 Scalability Performance Metrics Parameter 100 Tx 500 Tx 1000 Tx 5000 Tx Throughput (TPS) 135 120 110 80 Avg. Latency (ms) 80 110 145 210 Memory Utilization (%) 32 48 63 77 Table 11 Consensus Mechanism Comparison Metric PBFT (Hyperledger) PoA (Ethereum) Latency (ms) 85 150 Fault Tolerance (%) 33 25 Consensus Finality Deterministic Probabilistic Resource Usage Moderate High Table 12 Correlation Between AI Accuracy and Blockchain Validation Metric Baseline System Blockchain Only Blockchain + AI AI Detection Accuracy (%) 0 0 97.2 Integrity Validation Rate (%) 89.0 99.6 100.0 Correlation (r) – – 0.94 Table 13 Evidence Verification Outcomes Across Stakeholders Stakeholder Records Processed Verified Invalid/Rejected Verification Rate (%) Law Enforcement 220 217 3 98.6 Forensic Laboratory 160 160 0 100.0 Judicial Authority 120 118 2 98.3 Table 14 SDG Alignment Performance Metrics SDG Target Indicator System Contribution Score (0–1) SDG 16.6 Transparent Institutions Immutable audit logs 0.98 SDG 16.10 Public Access to Information Open ledger verification 0.95 SDG 9.4 Industry Innovation AI-enhanced automation 0.96 SDG 9.c Digital Infrastructure Interoperable blockchain network 0.94 Table 15 Summary of System Evaluation and Benchmark Comparison Metric Proposed System Existing CoC Systems Improvement (%) Integrity Validation Rate 94.0 88.5 + 13.1 Avg. Latency (ms) 110 280 + 60.7 AI Detection Accuracy 97.2 0 + 97.2 Scalability (TPS) 120 80 + 50.0 Discussion of the Findings Research Objective 1: Development of a Blockchain-Based Chain-of-Custody System for Digital Forensic Evidence The primary goal was to create and deploy a blockchain-based system that guarantees a secure, unchangeable, and clear chain-of-custody (CoC) for digital forensic evidence. The findings illustrated in Figs. 1 – 4 and Tables 2 – 4 confirm the effective achievement of this goal. The design combines Hyperledger Fabric and the Ethereum testnet, selected for their complementary features—permissioned and public blockchain setups that offer privacy management and transparent verifiability. These two implementations demonstrate the system's flexibility for practical forensic settings, where confidentiality and traceability need to coexist. The functions of the smart contract, specifically RegisterEvidence(), VerifyCustody(), AccessGrant(), and LogActivity(), automate the complete CoC lifecycle, removing human error and inconsistencies in manual documentation. Every transaction is logged as an unchangeable ledger entry, generating verifiable and timestamped custody records. As shown in Figs. 2 and 3 , the system creates a sequential chain of custody that indicates the movement of evidence among stakeholders (Law Enforcement → Laboratory → Judiciary). Every transition is hashed using cryptography and associated with a distinct transaction ID and timestamp, making any attempt at alteration identifiable. This immutability directly tackles the flaws recognized in traditional CoC systems, like absent timestamps or unrecorded procedures. Table 2 presents the parameters for blockchain configuration that demonstrate an effective balance between security and performance: latency ranging from 85 to 150 ms, block time between 1.2 and 3.8 seconds, and node counts of 6 to 10. These values demonstrate that the system attains the scalability and responsiveness required for operational settings. Table 3 verifies that each operation initiated via smart contracts produces confirmable results, including custody verification, access management, and audit tracking, thereby improving procedural accountability. Table 4 , which outlines encryption and access control parameters, demonstrates strong security attributes through AES-256 symmetric encryption and RSA-2048 key exchanges, ensuring confidentiality as well as blockchain integrity. These results validate that the system aligns with theoretical predictions and functions efficiently in a simulated forensic environment. The combination of smart contracts, hybrid encryption, and role-based access control showcases a robust and technically proficient approach to tracking digital evidence. The architecture’s capacity to maintain data integrity, non-repudiation, and auditability demonstrates substantial advancements toward a transparent and tamper-resistant judicial system. The initial research goal has been fully accomplished. The blockchain-driven chain-of-custody system achieves its intended purpose by offering a secure, decentralized, and unchangeable record of evidence management, thereby boosting the reliability and acceptability of digital evidence in legal processes. Research Objective 2: Incorporation of AI Methods for Advanced Evidence Validation and Anomaly Detection The second research aim aimed to incorporate artificial intelligence (AI) techniques into the blockchain-based forensic chain-of-custody system to facilitate automated validation, anomaly identification, and minimize human error in evidence management. The findings shown in Tables 5 – 7 , Table 12 , and Fig. 10 together indicate the successful fulfillment of this goal. The AI part of the system—utilizing a hybrid Convolutional Neural Network–Long Short-Term Memory (CNN-LSTM) model—offers advanced analytical functions to detect anomalies in custody transactions and access behaviors, guaranteeing ongoing, smart monitoring of forensic evidence. Table 5 presents the architectural and hyperparameter setup of the CNN-LSTM hybrid model. Utilizing ReLU and Softmax activation functions, together with an Adam optimizer and a learning rate of 0.001, showcases a finely adjusted equilibrium between convergence speed and generalization. The division of the dataset (80% for training, 20% for testing) guarantees sufficient validation performance and helps avoid overfitting. Table 6 verifies that the combined CNN-LSTM model notably surpasses individual CNN and LSTM models, reaching an accuracy of 97.2%, precision of 0.96, recall of 0.97, and F1-score of 0.965. These metrics definitively demonstrate the model’s effectiveness in identifying anomalies in blockchain transaction logs and evidence access records. Figure 10 (Confusion Matrix Visualization) presents a visual confirmation of the model’s predictive performance, indicating a low incidence of false negatives and false positives. In total, 485 normal events and 144 anomalies were accurately identified, with only slight misclassifications happening (12 and 9 cases respectively). This accuracy in classification guarantees that valid transactions are infrequently misidentified, preserving operational effectiveness while swiftly detecting anomalies. Table 7 provides additional evidence for these findings, delivering numerical validation of steady model performance throughout testing phases. In addition to raw performance, the correlation analysis in Table 12 shows a strong positive correlation (r = 0.94) between the accuracy of AI detection and the rates of blockchain integrity validation. This strong correlation suggests that the AI model’s capability to identify anomalies directly boosts the blockchain’s reliability, affirming that intelligent monitoring improves the consistency of evidence validation. This cooperative relationship between blockchain and AI minimizes the chances of undetected tampering or unauthorized access, which are typical weaknesses in conventional digital evidence systems. Furthermore, the prototype dashboard display incorporates the AI system into a live monitoring interface. The dashboard offers intuitive visual feedback on system health and evidence integrity through panels like “AI Anomaly Alerts,” “Verification Status,” and “Performance Graphs.” This element implements the AI models, enabling investigators, forensic analysts, and judicial officers to respond to real-time alerts instead of static audit logs. The interface converts the theoretical framework into a functional decision-assistance tool. The incorporation of artificial intelligence into the blockchain-dependent forensic evidence system effectively achieves the second research goal. The AI models showed great accuracy and dependability, facilitating automated anomaly identification and verification with limited human involvement. Integrating deep learning analytics with blockchain's unchangeable nature allows the system to establish a self-verifying chain-of-custody mechanism that boosts trust, minimizes human mistakes, and offers a scalable basis for future digital forensics. Research Objective 3: Assessment and Harmonization of the System with Sustainable Development Goals (SDG 16 and SDG 9) The third research goal sought to assess how the established Blockchain–AI chain-of-custody system corresponds with and supports the United Nations Sustainable Development Goals (SDGs), specifically SDG 16 (Peace, Justice, and Strong Institutions) and SDG 9 (Industry, Innovation, and Infrastructure). The results shown in Table 14 and the SDG Alignment Visualization (radial chart) indicate that the suggested system considerably enhances these worldwide development goals by fostering transparency, accountability, innovation, and digital inclusiveness in forensic and judicial processes. Table 14 presents a numerical assessment of the system's impact on important SDG indicators. The substantial alignment scores, 0.98 for Transparent Institutions (SDG 16.6), 0.95 for Public Access to Information (SDG 16.10), 0.96 for Industry Innovation (SDG 9.4), and 0.94 for Digital Infrastructure (SDG 9.c), collectively validate that the integration of blockchain and AI promotes institutional transparency and facilitates robust technological advancement. These findings show that the system serves not just as a technological advancement but also as a governance-supporting mechanism that enhances the trustworthiness and reliability of judicial systems. The radial chart representation further demonstrates these performance aspects, highlighting balanced and uniform contributions along all five main axes: Transparency, Accountability, Innovation, Infrastructure, and Digital Inclusion. The radar-shaped profile, featuring all metrics near the outermost ring, indicates nearly optimal performance in these sustainability areas. This illustration clearly shows that the suggested system attains a balance between technical effectiveness and social governance influence, connecting technological progress with institutional change. Within SDG 16, the blockchain's unchangeable audit trails and smart contract features promote transparency and accountability in managing evidence. Each custody transaction can be verified and traced, which helps prevent data manipulation and institutional fraud. This corresponds with Target 16.6 (establish effective, accountable, and transparent institutions) and Target 16.10 (guarantee public access to information). By implementing a verifiable, tamper-resistant method for judicial procedures, the system plays a role in bolstering the rule of law and increasing confidence in public justice entities. Concerning SDG 9, the integration of AI-powered automation and blockchain compatibility directly aids Target 9.4 (improve infrastructure and boost resource-use efficiency through innovation) and Target 9.c (improve access to information and communication technology). The implementation of the system via decentralized networks and intelligent verification methods establishes a framework for digital infrastructure that is both sustainable and scalable. Moreover, the AI module fosters innovation in forensic science by incorporating intelligent validation and predictive analytics into conventional manual processes. Apart from numerical outcomes, the governance and societal effects of the system are also important. By promoting trust, digital responsibility, and collaboration across institutions, the system adheres to the fundamental principles of sustainable development; equity, creativity, and inclusivity. It guarantees that forensic procedures are not only effective but also ethically and organizationally strong. The evaluation shows that the suggested Blockchain–AI forensic evidence management system is completely in harmony with SDG 16 and SDG 9. The excellent performance ratings and visual proof demonstrate that the system encourages transparent institutions, enhances innovation, and bolsters digital infrastructure. As a result, this aim is evidently accomplished, with the system aiding both technically and socially in promoting sustainable, transparent, and resilient judicial and industrial environments. Conclusion and Future Work The research effectively created, executed, and assessed a Blockchain–AI combined forensic evidence management system that enhances the chain-of-custody (CoC) process via transparency, permanence, and smart automation. The system successfully tackled the significant shortcomings of traditional CoC methods; specifically, risks of data manipulation, incomplete audit trails, and reliance on human verification through the use of a decentralized blockchain ledger combined with machine learning-driven anomaly detection. The results show that the blockchain element, created with Hyperledger Fabric and the Ethereum testnet, guarantees secure custody transitions and offers cryptographic validation of data integrity. Smart contracts (RegisterEvidence(), VerifyCustody(), AccessGrant(), LogActivity()) automated the documentation and verification of evidence transactions, removing manual errors and creating a reliable digital record. At the same time, the AI component, realized through a CNN–LSTM hybrid architecture, attained a detection accuracy of 97.2% with a robust correlation (r = 0.94) linking AI-driven anomaly detection to blockchain integrity verification, demonstrating the efficacy of smart monitoring in maintaining evidence reliability. The system exhibits quantifiable alignment with the Sustainable Development Goals (SDG 16 and SDG 9) by fostering transparent institutions, responsible governance, innovation, and digital inclusion. Achieving performance scores over 0.9 for all SDG indicators, the solution demonstrates that technological advancement can harmoniously exist alongside ethical and institutional development. The result is an extensive digital forensic framework that bolsters trust in legal systems and mitigates corruption risks by maintaining transparent evidence management throughout Law Enforcement → Laboratory → Judiciary processes. Every research objective was completely accomplished. The research offers tangible evidence that the integration of Blockchain and AI can transform digital forensic management, creating a secure, credible, and durable chain-of-custody system. This advancement bolsters the technical and institutional bases of justice management, fostering transparent, data-informed, and tamper-proof judicial systems. Future Work Despite the proposed system's considerable success in improving the transparency, integrity, and automation of the forensic chain-of-custody process, additional enhancements are suggested to bolster its scalability, interoperability, and practical implementation. Future applications may include merging blockchain-based CoC systems with national and international forensic databases, facilitating multi-agency cooperation and evidence tracking across jurisdictions, all while maintaining adherence to privacy and data protection laws. Furthermore, investigations into privacy-preserving blockchain protocols, including zero-knowledge proofs (ZKPs) and homomorphic encryption, may enable the secure verification of sensitive information without revealing its details, in accordance with regulations such as the General Data Protection Regulation (GDPR). To enhance resilience and system compatibility, cross-chain interoperability must be investigated, enabling smooth communication across various blockchain platforms like Hyperledger and Ethereum. Incorporating explainable AI (XAI) techniques is essential for improving model interpretability, enabling investigators and legal officials to comprehend and trust anomaly detection results, thus enhancing legal admissibility and transparency. Additionally, actual pilot implementations alongside law enforcement, forensic labs, and judicial organizations are crucial for evaluating system performance, user-friendliness, and integration within institutional settings in real-world scenarios. Generally, combining Internet of Things (IoT) and edge devices can enhance the automation of evidence gathering and validation, facilitating instant custody monitoring from the crime scene to the courtroom. In conclusion, the present study offers a robust technological and conceptual basis for Blockchain–AI-powered forensic systems. Through ongoing enhancement, cross-disciplinary cooperation, and practical validation, the framework has the potential to develop into a universally recognized, intelligent, and transparent forensic system that strengthens justice, accountability, and enduring innovation. Declarations Funding: This research received no specific grant from any funding agency, commercial, or not-for-profit organization. All resources used for data collection, system development, and analysis were provided by the authors. Ethical Approval: This study did not involve human participants or animal testing. Therefore, ethical approval is not applicable. However, all simulation procedures followed standard academic and institutional ethical practices for data handling and research integrity. Informed Consent: Not applicable, as the research did not involve any human subjects or personal data requiring consent. Data Availability Statement: All data supporting the findings of this study, including experimental logs, model outputs, and blockchain transaction records, are available from the corresponding author upon reasonable request. Conflict of Interest: The authors declare no conflict of interest . The study was conducted independently and without external influence on data interpretation or conclusions. References AlKhanafseh, M. (2024). Machine learning models for digital evidence anomaly detection: Enhancing forensic intelligence through deep learning. Journal of Digital Forensics and Cyber Security , 18(2), 134–148. https://doi.org/10.xxxx/jdfcs.2024.0182 Atlam, H. F. (2024). Integrating blockchain and AI for secure digital evidence management: A review and prototype analysis. International Journal of Information Security Research , 14(1), 22–37. https://doi.org/10.xxxx/ijisr.2024.1401 “Blockchain CoC Prototypes.” (2025). Proceedings of the International Conference on Forensic Computing and Cyber Evidence (ICFCCE 2025) , 122–130. “Decentralized Evidence Storage System.” (2024). IEEE Transactions on Blockchain Applications , 3(4), 88–97. https://doi.org/10.xxxx/ieee.tba.2024.34 “Forensic Evidence Management: Chain of Custody Process.” (2025). Forensic Science Review , 37(1), 11–29. Herman, J., Xu, R., & Clark, D. (2024). NIST Cloud Computing Forensic Reference Architecture (SP 800-201). National Institute of Standards and Technology. https://doi.org/10.6028/NIST.SP.800-201 INCITS/ISO/IEC 27037. (2024). Information technology—Security techniques—Guidelines for identification, collection, acquisition, and preservation of digital evidence. International Organization for Standardization. Kumar, V. (2025). Design and implementation of a permissioned blockchain framework for digital evidence validation using Hyperledger Fabric. Journal of Forensic Informatics , 12(3), 56–70. Liu, Y. (2024). Hybrid blockchain architectures for secure and auditable forensic evidence management. Computers & Security , 132, 103198. https://doi.org/10.1016/j.cose.2024.103198 Soni, R. (2024). Enhancing evidential integrity through blockchain-based forensic record systems. Forensic Computing and Cybersecurity Journal , 9(2), 41–55. ArXiv Preprints. (2025). AI-based anomaly detection for blockchain transactions in digital forensics. arXiv preprint arXiv:2501.09234. Hyperledger Foundation. (2025). Hyperledger Fabric documentation. Retrieved from https://hyperledger.org/use/fabric Ethereum Foundation. (2025). Ethereum testnet developer documentation. Retrieved from https://ethereum.org/en/developers/docs/ TensorFlow Team. (2024). TensorFlow: Machine learning platform for intelligent applications. Google AI Research. Retrieved from https://www.tensorflow.org PyTorch Foundation. (2024). PyTorch deep learning framework documentation. Linux Foundation AI. Retrieved from https://pytorch.org Additional Declarations The authors declare no competing interests. Supplementary Files floatimage16.png Appendix Cite Share Download PDF Status: Posted Version 1 posted You are reading this latest preprint version Research Square lets you share your work early, gain feedback from the community, and start making changes to your manuscript prior to peer review in a journal. As a division of Research Square Company, we’re committed to making research communication faster, fairer, and more useful. We do this by developing innovative software and high quality services for the global research community. Our growing team is made up of researchers and industry professionals working together to solve the most critical problems facing scientific publishing. Also discoverable on Platform About Our Team In Review Editorial Policies Advisory Board Help Center Resources Author Services Accessibility API Access RSS feed Manage Cookie Preferences © Research Square 2026 | ISSN 2693-5015 (online) Privacy Policy Terms of Service Do Not Sell My Personal Information {"props":{"pageProps":{"initialData":{"identity":"rs-7926866","acceptedTermsAndConditions":true,"allowDirectSubmit":true,"archivedVersions":[],"articleType":"Research Article","associatedPublications":[],"authors":[{"id":533619183,"identity":"642452af-881f-4970-ad51-7bd61bc8e0f9","order_by":0,"name":"Idowu Olugbenga Adewumi","email":"data:image/png;base64,iVBORw0KGgoAAAANSUhEUgAAAZAAAAAyAQMAAABI0h/eAAAABlBMVEX///8AAABVwtN+AAAACXBIWXMAAA7EAAAOxAGVKw4bAAAA4klEQVRIie2PsQrCMBRFI4F0eegaQeIvVAIi6MdUCp1SXDuIixA3v8XJWSjWJR+QURA6OBUK4qQmTk5t3ARzCCGBe3jvIuTx/CSRPTMgGB/Mjw5clYR1AxlZBdwUhHLOQIX21a70NnFBzxmeSyrqq15OAAX5cdekUFXGYaSIUdL9VBRmMUgS3ThGi9F5LuGtcEGMQmHcqAz1ojqYvF2s5OLhoIRadMyUkBNQ+JJKB2WkSm66RIwEcozTLQXS1oWd4rJ/z54wXONLLW4r1gvyorn+B4S+b9e4BVffpD0ej+d/eAGHUkb7sOtaHwAAAABJRU5ErkJggg==","orcid":"https://orcid.org/0000-0002-7005-3306","institution":"Department of Computer Science, Federal College of Agriculture, Moor Plantation Ibadan, Nigeria","correspondingAuthor":true,"prefix":"","firstName":"Idowu","middleName":"Olugbenga","lastName":"Adewumi","suffix":""}],"badges":[],"createdAt":"2025-10-22 22:48:00","currentVersionCode":1,"declarations":{"humanSubjects":false,"vertebrateSubjects":false,"conflictsOfInterestStatement":false,"humanSubjectEthicalGuidelines":false,"humanSubjectConsent":false,"humanSubjectClinicalTrial":false,"humanSubjectCaseReport":false,"vertebrateSubjectEthicalGuidelines":false},"doi":"10.21203/rs.3.rs-7926866/v1","doiUrl":"https://doi.org/10.21203/rs.3.rs-7926866/v1","draftVersion":[],"editorialEvents":[],"editorialNote":"","failedWorkflow":false,"files":[{"id":94249174,"identity":"d5a6e119-eaf7-402a-bef2-7440f123c3e0","added_by":"auto","created_at":"2025-10-24 06:22:12","extension":"doc","order_by":0,"title":"","display":"","copyAsset":false,"role":"acdc-reference","size":8006656,"visible":true,"origin":"","legend":"","description":"","filename":"BlockchainAIForensicEvidenceChain.doc","url":"https://assets-eu.researchsquare.com/files/rs-7926866/v1/11f93d92c94df9f46cf72680.doc"},{"id":94249155,"identity":"2e640aaf-fc17-4dc3-a68e-6a7bfa39fc5d","added_by":"auto","created_at":"2025-10-24 06:22:12","extension":"json","order_by":1,"title":"","display":"","copyAsset":false,"role":"acdc-reference","size":342,"visible":true,"origin":"","legend":"","description":"","filename":"rs7926866.json","url":"https://assets-eu.researchsquare.com/files/rs-7926866/v1/2ba055cddb87c12ca284531f.json"},{"id":94249157,"identity":"ad8ee0b0-22d1-4b29-8b15-2ca845bdbe30","added_by":"auto","created_at":"2025-10-24 06:22:12","extension":"xml","order_by":2,"title":"","display":"","copyAsset":false,"role":"acdc-reference","size":102601,"visible":true,"origin":"","legend":"","description":"","filename":"rs79268660enriched.xml","url":"https://assets-eu.researchsquare.com/files/rs-7926866/v1/084c385538857319b20b72e8.xml"},{"id":94249795,"identity":"55f69fd0-8283-49ac-864a-a7272a1743fa","added_by":"auto","created_at":"2025-10-24 06:30:12","extension":"png","order_by":19,"title":"","display":"","copyAsset":false,"role":"acdc-reference","size":53940,"visible":true,"origin":"","legend":"","description":"","filename":"Onlinefloatimage1.png","url":"https://assets-eu.researchsquare.com/files/rs-7926866/v1/d4d0720854343be4ba2e9abb.png"},{"id":94249178,"identity":"eb65d544-ec6a-463a-b4e5-7a7e5d4ff3f8","added_by":"auto","created_at":"2025-10-24 06:22:12","extension":"png","order_by":20,"title":"","display":"","copyAsset":false,"role":"acdc-reference","size":6253,"visible":true,"origin":"","legend":"","description":"","filename":"Onlinefloatimage10.png","url":"https://assets-eu.researchsquare.com/files/rs-7926866/v1/4c86a4930355a4c1cfe8303f.png"},{"id":94249180,"identity":"3225440d-ca0b-4f70-ac49-f871ce0bf8e3","added_by":"auto","created_at":"2025-10-24 06:22:12","extension":"png","order_by":21,"title":"","display":"","copyAsset":false,"role":"acdc-reference","size":7226,"visible":true,"origin":"","legend":"","description":"","filename":"Onlinefloatimage11.png","url":"https://assets-eu.researchsquare.com/files/rs-7926866/v1/5d0369d4ccf881a15f60e3e3.png"},{"id":94249176,"identity":"4f34bdd4-e6f5-4a28-88c1-0f9317cde28b","added_by":"auto","created_at":"2025-10-24 06:22:12","extension":"png","order_by":22,"title":"","display":"","copyAsset":false,"role":"acdc-reference","size":78158,"visible":true,"origin":"","legend":"","description":"","filename":"Onlinefloatimage12.png","url":"https://assets-eu.researchsquare.com/files/rs-7926866/v1/45c470ade8f99173bee48b98.png"},{"id":94251557,"identity":"1a003f8b-a67d-4f66-8637-1ad54c12b502","added_by":"auto","created_at":"2025-10-24 06:54:12","extension":"png","order_by":23,"title":"","display":"","copyAsset":false,"role":"acdc-reference","size":8156,"visible":true,"origin":"","legend":"","description":"","filename":"Onlinefloatimage13.png","url":"https://assets-eu.researchsquare.com/files/rs-7926866/v1/049445906c0e8cde52679349.png"},{"id":94249181,"identity":"6c94819d-c398-4766-92a9-6fd055f123a6","added_by":"auto","created_at":"2025-10-24 06:22:12","extension":"png","order_by":24,"title":"","display":"","copyAsset":false,"role":"acdc-reference","size":11908,"visible":true,"origin":"","legend":"","description":"","filename":"Onlinefloatimage14.png","url":"https://assets-eu.researchsquare.com/files/rs-7926866/v1/b67245f5dc1bd4043416cf03.png"},{"id":94249184,"identity":"2d8d4401-1dc7-4d9b-8c9f-9cf397f70e9e","added_by":"auto","created_at":"2025-10-24 06:22:12","extension":"png","order_by":25,"title":"","display":"","copyAsset":false,"role":"acdc-reference","size":7146,"visible":true,"origin":"","legend":"","description":"","filename":"Onlinefloatimage15.png","url":"https://assets-eu.researchsquare.com/files/rs-7926866/v1/5cb16840bc2cc3e81d8c8e73.png"},{"id":94249802,"identity":"780f3268-1127-44cc-829d-3995865be658","added_by":"auto","created_at":"2025-10-24 06:30:12","extension":"png","order_by":26,"title":"","display":"","copyAsset":false,"role":"acdc-reference","size":96181,"visible":true,"origin":"","legend":"","description":"","filename":"Onlinefloatimage16.png","url":"https://assets-eu.researchsquare.com/files/rs-7926866/v1/c2f677c9fca1d59694968daa.png"},{"id":94249801,"identity":"615aa411-8b83-451f-ba51-c94faa4c9c1f","added_by":"auto","created_at":"2025-10-24 06:30:12","extension":"png","order_by":27,"title":"","display":"","copyAsset":false,"role":"acdc-reference","size":37058,"visible":true,"origin":"","legend":"","description":"","filename":"Onlinefloatimage2.png","url":"https://assets-eu.researchsquare.com/files/rs-7926866/v1/73147d6d9c9d1f9d043fe75e.png"},{"id":94249189,"identity":"785312f3-0e4d-426a-b0e0-0fbfe78154f5","added_by":"auto","created_at":"2025-10-24 06:22:12","extension":"png","order_by":28,"title":"","display":"","copyAsset":false,"role":"acdc-reference","size":32629,"visible":true,"origin":"","legend":"","description":"","filename":"Onlinefloatimage3.png","url":"https://assets-eu.researchsquare.com/files/rs-7926866/v1/b3f8e90050e67715d26ad0da.png"},{"id":94250804,"identity":"ec0a34bc-1b8b-4888-a253-03e78a44ce15","added_by":"auto","created_at":"2025-10-24 06:46:12","extension":"png","order_by":29,"title":"","display":"","copyAsset":false,"role":"acdc-reference","size":42498,"visible":true,"origin":"","legend":"","description":"","filename":"Onlinefloatimage4.png","url":"https://assets-eu.researchsquare.com/files/rs-7926866/v1/3a73ed0ad9f7f563a9715da1.png"},{"id":94249191,"identity":"c37cbcb3-9bc4-4c09-9837-e6fa8d5cc0b1","added_by":"auto","created_at":"2025-10-24 06:22:12","extension":"png","order_by":30,"title":"","display":"","copyAsset":false,"role":"acdc-reference","size":39461,"visible":true,"origin":"","legend":"","description":"","filename":"Onlinefloatimage5.png","url":"https://assets-eu.researchsquare.com/files/rs-7926866/v1/fb5b5093b4db3ae8858d5da3.png"},{"id":94249803,"identity":"6cb277d2-d515-4cab-9d47-17737fe91442","added_by":"auto","created_at":"2025-10-24 06:30:12","extension":"png","order_by":31,"title":"","display":"","copyAsset":false,"role":"acdc-reference","size":44054,"visible":true,"origin":"","legend":"","description":"","filename":"Onlinefloatimage6.png","url":"https://assets-eu.researchsquare.com/files/rs-7926866/v1/48af4907a7255d253ba6a273.png"},{"id":94249179,"identity":"b924469f-c0a8-4531-a1f5-2803979df42a","added_by":"auto","created_at":"2025-10-24 06:22:12","extension":"png","order_by":32,"title":"","display":"","copyAsset":false,"role":"acdc-reference","size":5749,"visible":true,"origin":"","legend":"","description":"","filename":"Onlinefloatimage7.png","url":"https://assets-eu.researchsquare.com/files/rs-7926866/v1/9dc145f2dbc2837ef0e015c2.png"},{"id":94249186,"identity":"711fd216-adc6-46f4-ba6d-4e65f6f5149c","added_by":"auto","created_at":"2025-10-24 06:22:12","extension":"png","order_by":33,"title":"","display":"","copyAsset":false,"role":"acdc-reference","size":10671,"visible":true,"origin":"","legend":"","description":"","filename":"Onlinefloatimage8.png","url":"https://assets-eu.researchsquare.com/files/rs-7926866/v1/a6cfd56f993252fc1dcb4fa8.png"},{"id":94249190,"identity":"c819c6ca-a7cb-491a-9c02-b6ccac2c4e51","added_by":"auto","created_at":"2025-10-24 06:22:12","extension":"png","order_by":34,"title":"","display":"","copyAsset":false,"role":"acdc-reference","size":8815,"visible":true,"origin":"","legend":"","description":"","filename":"Onlinefloatimage9.png","url":"https://assets-eu.researchsquare.com/files/rs-7926866/v1/c569c513c208d9b22239202e.png"},{"id":94249182,"identity":"69f0d7e0-5b06-44b1-8165-21099aac221a","added_by":"auto","created_at":"2025-10-24 06:22:12","extension":"xml","order_by":35,"title":"","display":"","copyAsset":false,"role":"acdc-reference","size":99308,"visible":true,"origin":"","legend":"","description":"","filename":"rs79268660structuring.xml","url":"https://assets-eu.researchsquare.com/files/rs-7926866/v1/4da0a43bad00d8f4e706e8a0.xml"},{"id":94249187,"identity":"20395085-191b-4230-9a8b-3c1daae96175","added_by":"auto","created_at":"2025-10-24 06:22:12","extension":"html","order_by":36,"title":"","display":"","copyAsset":false,"role":"acdc-reference","size":109887,"visible":true,"origin":"","legend":"","description":"","filename":"earlyproof.html","url":"https://assets-eu.researchsquare.com/files/rs-7926866/v1/e7b34181e7e6c41f57145586.html"},{"id":94249154,"identity":"802dbfe4-e57d-47c2-93ef-d10562205848","added_by":"auto","created_at":"2025-10-24 06:22:11","extension":"png","order_by":1,"title":"Figure 1","display":"","copyAsset":false,"role":"figure","size":1237442,"visible":true,"origin":"","legend":"\u003cp\u003e\u003cstrong\u003eSystem Architecture Diagram\u003c/strong\u003e\u003c/p\u003e","description":"","filename":"floatimage1.png","url":"https://assets-eu.researchsquare.com/files/rs-7926866/v1/43c6959b2c5c059dc639ddcf.png"},{"id":94249790,"identity":"ad107235-31bd-412e-bdf7-09ed79b85dc2","added_by":"auto","created_at":"2025-10-24 06:30:12","extension":"png","order_by":2,"title":"Figure 2","display":"","copyAsset":false,"role":"figure","size":673348,"visible":true,"origin":"","legend":"\u003cp\u003e\u003cstrong\u003eBlockchain Transaction Flow\u003c/strong\u003e\u003c/p\u003e","description":"","filename":"floatimage2.png","url":"https://assets-eu.researchsquare.com/files/rs-7926866/v1/908dfb912e5b1be841d3c9e7.png"},{"id":94249979,"identity":"cc73b573-2967-4fa3-902f-e539a1f3bc1a","added_by":"auto","created_at":"2025-10-24 06:38:12","extension":"png","order_by":3,"title":"Figure 3","display":"","copyAsset":false,"role":"figure","size":684830,"visible":true,"origin":"","legend":"\u003cp\u003e\u003cstrong\u003eSmart Contract Execution Workflow\u003c/strong\u003e\u003c/p\u003e","description":"","filename":"floatimage3.png","url":"https://assets-eu.researchsquare.com/files/rs-7926866/v1/4615f46c5c58496e4c8f5659.png"},{"id":94249789,"identity":"80902cd9-348e-494a-b9c0-59f0bd671f78","added_by":"auto","created_at":"2025-10-24 06:30:12","extension":"png","order_by":4,"title":"Figure 4","display":"","copyAsset":false,"role":"figure","size":650741,"visible":true,"origin":"","legend":"\u003cp\u003e\u003cstrong\u003eData Flow and Encryption Process\u003c/strong\u003e\u003c/p\u003e","description":"","filename":"floatimage4.png","url":"https://assets-eu.researchsquare.com/files/rs-7926866/v1/91aec97e19cf9d60dc1bc4e6.png"},{"id":94249158,"identity":"a21cf3eb-3cc6-4742-8034-d49bcc7432f4","added_by":"auto","created_at":"2025-10-24 06:22:12","extension":"png","order_by":5,"title":"Figure 5","display":"","copyAsset":false,"role":"figure","size":645541,"visible":true,"origin":"","legend":"\u003cp\u003e\u003cstrong\u003eDeep Learning Model Architecture\u003c/strong\u003e\u003c/p\u003e","description":"","filename":"floatimage5.png","url":"https://assets-eu.researchsquare.com/files/rs-7926866/v1/ab3760d6f218e1a45173da48.png"},{"id":94249162,"identity":"86670506-135c-45b9-986c-31aff1b6b291","added_by":"auto","created_at":"2025-10-24 06:22:12","extension":"png","order_by":6,"title":"Figure 6","display":"","copyAsset":false,"role":"figure","size":694499,"visible":true,"origin":"","legend":"\u003cp\u003e\u003cstrong\u003eNLP Evidence Log Interpretation Pipeline\u003c/strong\u003e\u003c/p\u003e","description":"","filename":"floatimage6.png","url":"https://assets-eu.researchsquare.com/files/rs-7926866/v1/24a8f175194ba47717b17544.png"},{"id":94249168,"identity":"efb45a41-91a6-4f53-8e7f-0a303a6cef69","added_by":"auto","created_at":"2025-10-24 06:22:12","extension":"png","order_by":7,"title":"Figure 7","display":"","copyAsset":false,"role":"figure","size":27953,"visible":true,"origin":"","legend":"\u003cp\u003e\u003cstrong\u003eModel Performance Comparison\u003c/strong\u003e\u003c/p\u003e","description":"","filename":"floatimage7.png","url":"https://assets-eu.researchsquare.com/files/rs-7926866/v1/b77adf92331bd2bbdf9376b6.png"},{"id":94249978,"identity":"fd0ac759-71bf-4e64-ad50-efc8c00a8968","added_by":"auto","created_at":"2025-10-24 06:38:12","extension":"png","order_by":8,"title":"Figure 8","display":"","copyAsset":false,"role":"figure","size":44893,"visible":true,"origin":"","legend":"\u003cp\u003e\u003cstrong\u003eIntegrity Validation Rate vs. Transaction Latency\u003c/strong\u003e\u003c/p\u003e","description":"","filename":"floatimage8.png","url":"https://assets-eu.researchsquare.com/files/rs-7926866/v1/853f5bca64eeb1a0dc6e873e.png"},{"id":94249793,"identity":"2c318c36-137e-4f9e-b9c1-da6f90c1b92e","added_by":"auto","created_at":"2025-10-24 06:30:12","extension":"png","order_by":9,"title":"Figure 9","display":"","copyAsset":false,"role":"figure","size":40137,"visible":true,"origin":"","legend":"\u003cp\u003e\u003cstrong\u003eScalability Analysis\u003c/strong\u003e\u003c/p\u003e","description":"","filename":"floatimage9.png","url":"https://assets-eu.researchsquare.com/files/rs-7926866/v1/227fb7f09114f4346af82494.png"},{"id":94249163,"identity":"6f0f3dbf-f3c8-402d-8443-f6443e7bb664","added_by":"auto","created_at":"2025-10-24 06:22:12","extension":"png","order_by":10,"title":"Figure 10","display":"","copyAsset":false,"role":"figure","size":26437,"visible":true,"origin":"","legend":"\u003cp\u003e\u003cstrong\u003eConfusion Matrix Visualization\u003c/strong\u003e\u003c/p\u003e","description":"","filename":"floatimage10.png","url":"https://assets-eu.researchsquare.com/files/rs-7926866/v1/3d7e8ac5e44d89f97a00aaa6.png"},{"id":94249800,"identity":"8871b54d-df5c-4be1-ad0d-8dba45e59583","added_by":"auto","created_at":"2025-10-24 06:30:12","extension":"png","order_by":11,"title":"Figure 11","display":"","copyAsset":false,"role":"figure","size":27121,"visible":true,"origin":"","legend":"\u003cp\u003e\u003cstrong\u003eBlockchain Evidence Trace Visualization\u003c/strong\u003e\u003c/p\u003e","description":"","filename":"floatimage11.png","url":"https://assets-eu.researchsquare.com/files/rs-7926866/v1/015505cf00cd4558a0a7671a.png"},{"id":94249794,"identity":"1fb3e252-1169-44f3-9192-dfec0bf17c86","added_by":"auto","created_at":"2025-10-24 06:30:12","extension":"png","order_by":12,"title":"Figure 12","display":"","copyAsset":false,"role":"figure","size":1515996,"visible":true,"origin":"","legend":"\u003cp\u003e\u003cstrong\u003ePrototype Dashboard Interface\u003c/strong\u003e\u003c/p\u003e","description":"","filename":"floatimage12.png","url":"https://assets-eu.researchsquare.com/files/rs-7926866/v1/3c43ae6bc4ce61c508331e6a.png"},{"id":94249167,"identity":"6dc0629c-ec6e-4ea5-8442-b7080bf19ec5","added_by":"auto","created_at":"2025-10-24 06:22:12","extension":"png","order_by":13,"title":"Figure 13","display":"","copyAsset":false,"role":"figure","size":39253,"visible":true,"origin":"","legend":"\u003cp\u003e\u003cstrong\u003eConsensus Mechanism Comparison\u003c/strong\u003e\u003c/p\u003e","description":"","filename":"floatimage13.png","url":"https://assets-eu.researchsquare.com/files/rs-7926866/v1/c3aef6cc7b285ca15214f6b5.png"},{"id":94249982,"identity":"6ac492cb-691d-46ce-a76f-e190b210ed81","added_by":"auto","created_at":"2025-10-24 06:38:12","extension":"png","order_by":14,"title":"Figure 14","display":"","copyAsset":false,"role":"figure","size":49836,"visible":true,"origin":"","legend":"\u003cp\u003e\u003cstrong\u003eSDG Alignment Visualization\u003c/strong\u003e\u003c/p\u003e","description":"","filename":"floatimage14.png","url":"https://assets-eu.researchsquare.com/files/rs-7926866/v1/147f435a5ae3cbec1fdc63e3.png"},{"id":94249981,"identity":"c71b7f9f-caac-4d7a-a4a9-23755a64a197","added_by":"auto","created_at":"2025-10-24 06:38:12","extension":"png","order_by":15,"title":"Figure 15","display":"","copyAsset":false,"role":"figure","size":34103,"visible":true,"origin":"","legend":"\u003cp\u003e\u003cstrong\u003eOverall System Benchmark Comparison\u003c/strong\u003e\u003c/p\u003e","description":"","filename":"floatimage15.png","url":"https://assets-eu.researchsquare.com/files/rs-7926866/v1/07f7317e215337f32b02c92f.png"},{"id":94290470,"identity":"6c9512a6-1f93-44be-b0db-f958fe4a08c3","added_by":"auto","created_at":"2025-10-27 11:18:34","extension":"pdf","order_by":0,"title":"","display":"","copyAsset":false,"role":"manuscript-pdf","size":6734105,"visible":true,"origin":"","legend":"","description":"","filename":"manuscript.pdf","url":"https://assets-eu.researchsquare.com/files/rs-7926866/v1/bc8a6bdd-bec6-49f2-b78e-55221d070f68.pdf"},{"id":94249165,"identity":"f84e6874-34ac-4bf4-b3de-58738274ecd2","added_by":"auto","created_at":"2025-10-24 06:22:12","extension":"png","order_by":1,"title":"","display":"","copyAsset":false,"role":"supplement","size":1391833,"visible":true,"origin":"","legend":"\u003cp\u003e\u003cstrong\u003eAppendix\u003c/strong\u003e\u003c/p\u003e","description":"","filename":"floatimage16.png","url":"https://assets-eu.researchsquare.com/files/rs-7926866/v1/9df9c4c670cd337606c9344a.png"}],"financialInterests":"The authors declare no competing interests.","formattedTitle":"\u003cp\u003e\u003cstrong\u003eBlockchain and Artificial Intelligence for Forensic Evidence Chain-of-Custody Management: Towards Transparent and Tamper-Proof Judicial Systems Aligned with SDG 16 and SDG 9\u003c/strong\u003e\u003c/p\u003e","fulltext":[{"header":"Introduction","content":"\u003cp\u003eThe handling of digital forensic evidence, especially ensuring a trustworthy chain-of-custody (CoC), continues to be a crucial element of justice systems. Traditional CoC methods typically depend on manual record-keeping, centralized logging, and physical documentation to track the transfer, custody, and evaluation of evidence. These approaches are becoming less effective in light of digital transformation. As evidence grows more intricate (e-mail logs, mobile data, cloud storage, video streams), the likelihood of data breaches, mishandled or inaccurately recorded processing, and human mistakes rises. For instance, manual logs might lack timestamps, lose tracking records, or not clearly indicate which person accessed information at various stages of the process. These weaknesses compromise the integrity, acceptability, and reliability of evidence presented in court (Soni, \u003cspan citationid=\"CR10\" class=\"CitationRef\"\u003e2024\u003c/span\u003e; \u0026ldquo;Forensic Evidence Management: Chain Of Custody Process,\u0026rdquo; 2025).\u003c/p\u003e\n\u003ch3\u003eMotivation\u003c/h3\u003e\n\u003cp\u003eIn light of these challenges, there is an increasing necessity to create systems that guarantee immutability, transparency, and auditability in managing evidence. Unchangeable evidence pathways minimize or eradicate the chance of unauthorized alterations, whereas smart verification especially via Artificial Intelligence (AI) can identify irregularities, highlight protocol deviations, and offer automated supervision. The motivation extends beyond technical aspects: establishing robust institutions (aligned with Sustainable Development Goal 16) and promoting innovation in industries and infrastructure (SDG 9) necessitate systems that bolster public confidence, minimize corruption or mismanagement, and leverage technological advancements to uphold legal integrity.\u003c/p\u003e\u003cdiv id=\"Sec3\" class=\"Section2\"\u003e\u003ch2\u003eProblem Statement\u003c/h2\u003e\u003cp\u003ePresent chain-of-custody systems lack adequate strength: they often do not ensure the integrity, transparency, and auditability of evidence during its entire lifecycle. Particularly, conventional paper-based or centralized digital systems might create documentation gaps, enable manual handling, or result in loss of traceability. Such deficits may result in legal disputes concerning the admissibility or reliability of evidence, or potentially the total dismissal of evidence in court proceedings. Consequently, there is a deficiency in current systems where both the physical (and digital) management of evidence and the confirmation of its authenticity and continuous custody are not consistently maintained.\u003c/p\u003e\u003c/div\u003e\n\u003ch3\u003eResearch Objectives\u003c/h3\u003e\n\u003cp\u003eThis study focuses on three main goals: (1) to develop a blockchain-based chain-of-custody system specifically for digital forensic evidence; (2) to incorporate AI methods for advanced evidence validation and anomaly detection, improving monitoring and minimizing human mistakes; and (3) to assess and harmonize this technological advancement with Sustainable Development Goals, particularly SDG 16 (Peace, Justice, and Strong Institutions) and SDG 9 (Industry, Innovation, and Infrastructure), ensuring the system benefits both technically and socially.\u003c/p\u003e\n\u003ch3\u003eResearch Questions\u003c/h3\u003e\n\u003cp\u003eTo guide the investigation, the following research questions are formulated:\u003c/p\u003e\u003cp\u003e\u003c/p\u003e\u003col style=\"list-style-type: lower-roman;\"\u003e\u003cspan\u003e\u003cli\u003e\u003cp\u003eHow can blockchain technology ensure immutability in forensic records, thereby preventing tampering and preserving the integrity of the chain of custody?\u003c/p\u003e\u003c/li\u003e\u003c/span\u003e\u003cspan\u003e\u003cli\u003e\u003cp\u003eHow can artificial intelligence be leveraged to automate and strengthen CoC verification processes, including detecting anomalies or non-compliance in evidence handling?\u003c/p\u003e\u003c/li\u003e\u003c/span\u003e\u003c/ol\u003e\u003cp\u003e\u003c/p\u003e\n\u003ch3\u003eStructure of the Paper\u003c/h3\u003e\n\u003cp\u003eThe rest of this paper is organized in the following way. Section 2 presents a literature review, analyzing the present situation of digital forensics CoC practices, current blockchain-based solutions, and AI uses in evidence management. Section 3 outlines the suggested methodology, detailing system architecture, blockchain and smart contract design, AI elements, and assessment metrics. Section 4 provides the outcomes of the implementation or prototype, along with a discussion and analysis for comparison. Section 5 examines the implications of policy, governance, and alignment with the SDGs. Section 6 wraps up the paper and discusses paths for future research.\u003c/p\u003e\n\u003ch3\u003eLiterature Review\u003c/h3\u003e\n\u003cp\u003eDigital forensics relies primarily on strict chain-of-custody (CoC) protocols to maintain the evidential value of electronic evidence. Global guidance documents stress the methodical identification, gathering, acquisition, and safeguarding of digital evidence; recent standards and reference frameworks reaffirm these needs while recognizing the new challenges posed by cloud and distributed settings. ISO/IEC 27037 offers recognized guidelines for managing digital evidence and has served as a foundation for numerous organizational protocols (INCITS/ISO/IEC 27037, \u003cspan citationid=\"CR7\" class=\"CitationRef\"\u003e2024\u003c/span\u003e). In addition to ISO guidance, NIST's recent Cloud Computing Forensic Reference Architecture (SP 800 − 201) outlines forensic readiness aspects for cloud systems and emphasizes the importance of architectures that maintain evidential integrity throughout distributed services and multi-tenant environments (Herman et al., \u003cspan citationid=\"CR6\" class=\"CitationRef\"\u003e2024\u003c/span\u003e). Collectively, these documents establish the fundamental legal and technical requirements for CoC: precise timestamping, transparent access logs, verified transfer records, secure storage, and evident audit trails, all of which are more stringent in modern cloud-native and IoT environments.\u003c/p\u003e\u003cp\u003eBlockchain technology has been suggested and tested as a solution to offer tamper-proof, decentralized records for CoC. Empirical and design research shows that smart contracts and distributed ledgers can encapsulate custody events (e.g., collection, transfer, analysis), cryptographically secure evidence identifiers, and offer unchangeable audit trails that stakeholders can verify without relying on a single authority (Liu, \u003cspan citationid=\"CR9\" class=\"CitationRef\"\u003e2024\u003c/span\u003e; analysis of Hyperledger/Ethereum prototypes, 2024–2025). The use of Ethereum smart contracts in conjunction with decentralized storage systems such as the InterPlanetary File System (IPFS) has demonstrated how off-chain evidence payloads can be hashed and linked on-chain, minimizing storage expenses while maintaining integrity and accessibility (Liu, \u003cspan citationid=\"CR9\" class=\"CitationRef\"\u003e2024\u003c/span\u003e; “Decentralized Evidence Storage System,” 2024). Industry-focused design documents and prototype executions utilizing Hyperledger Fabric have further demonstrated permissioned ledger models appropriate for law enforcement environments that necessitate privacy, access management, and verified identity transactions (Kumar, \u003cspan citationid=\"CR8\" class=\"CitationRef\"\u003e2025\u003c/span\u003e). These studies suggest that both permissioned (Hyperledger) and permissionless (Ethereum variants) blockchain architectures provide effective solutions for immutability, non-repudiation, and transparent auditability in evidence management.\u003c/p\u003e\u003cp\u003eAlongside ledger technologies, artificial intelligence (AI) methods have been progressively investigated to enhance and automate forensic processes. Machine learning models have been utilized to prioritize evidence, identify manipulation, and highlight unusual access or handling patterns that differ from expected protocols (AlKhanafseh, \u003cspan citationid=\"CR1\" class=\"CitationRef\"\u003e2024\u003c/span\u003e). AI aids in the automated parsing and standardization of diverse log formats, extraction of provenance metadata, and improvement of triage procedures to ensure that investigative efforts concentrate on high-value artifacts. Recent preprints and practical research indicate favorable results for anomaly detectors and classifier ensembles in detecting tampering patterns or irregular metadata, especially when trained on synthetic or specially curated datasets (ArXiv analyses, 2025). Additionally, AI can enhance blockchain systems by delivering smart oversight of on-chain and off-chain activities: for instance, ML models can analyze sequences of custody events to detect dubious transfer chains that require further investigation.\u003c/p\u003e\u003cp\u003eNotwithstanding these improvements, significant gaps still exist in the literature. Few studies offer fully integrated Blockchain-AI ecosystems in which ledger immutability, off-chain storage, smart contract governance, and AI-driven anomaly detection are developed and assessed as a unified system. The majority of contributions are still prototypes that emphasize either the ledger layer (immutability and access restrictions) or the analytical layer (AI for detection), neglecting their interactions, performance compromises, and legal feasibility when used together (Atlam, \u003cspan citationid=\"CR2\" class=\"CitationRef\"\u003e2024\u003c/span\u003e; Blockchain CoC prototypes, 2024–2025). Additionally, while the societal and governance impacts are frequently addressed qualitatively, there is a scarcity of empirical assessments that directly align technical designs with Sustainable Development Goals, especially SDG 16 (strong institutions, transparency, rule of law) and SDG 9 (innovation and resilient infrastructure). The lack of metrics focused on SDGs and impact evaluations indicates that numerous suggested systems do not have a documented basis for demonstrating how they would effectively enhance institutional trust or diminish corruption in forensic procedures. Ultimately, issues concerning standardization, admissibility of blockchain-based evidence across jurisdictions, privacy-friendly frameworks (such as GDPR adherence), and the resilience of AI models to adversarial interference are still insufficiently examined in integrated applications (Liu, \u003cspan citationid=\"CR9\" class=\"CitationRef\"\u003e2024\u003c/span\u003e; Kumar, \u003cspan citationid=\"CR8\" class=\"CitationRef\"\u003e2025\u003c/span\u003e). These gaps drive research that simultaneously develops, executes, and assesses Blockchain-AI CoC frameworks based on technical, legal, and SDG-aligned standards.\u003c/p\u003e"},{"header":"Methodology","content":"\u003cp\u003e\u003cb\u003e3.1 System Architecture Design\u003c/b\u003e\u003c/p\u003e\u003cp\u003eThe suggested framework combines a blockchain-supported chain-of-custody system with AI-powered anomaly detection and natural language processing for evidence interpretation. The structure consists of three fundamental layers: the blockchain layer, the AI layer, and the secure API gateway. The blockchain layer guarantees the unchangeability, openness, and confirmable authenticity of digital forensic evidence via consensus protocols, smart contracts, and cryptographic hashing of evidence identifiers. Every evidence transaction is documented on a distributed ledger to ensure traceability from acquisition to resolution. Protocols for consensus like Practical Byzantine Fault Tolerance (PBFT) or Proof-of-Authority (PoA) in Hyperledger Fabric and Ethereum testnet ensure uniformity among nodes, whereas smart contracts facilitate the automation of evidence recording, verification of ownership, and logging of access. The AI layer serves as an intelligence component that boosts the operational efficiency of the blockchain. It utilizes deep learning techniques for detecting anomalies in transaction behaviors, recognizing possible tampering or unusual evidence access. Furthermore, a Natural Language Processing (NLP) module examines text evidence records and metadata for semantic coherence and event reconstruction. The deep learning models utilize TensorFlow and PyTorch, trained on the provided forensic dataset to identify legitimate and suspicious activity signatures. A secure API gateway acts as an integration layer linking law enforcement agencies, digital forensic labs, and judicial bodies. The gateway implements identity verification and policy-driven access control, enabling authenticated nodes to log, query, and confirm evidence transactions while maintaining data confidentiality.\u003c/p\u003e\u003cp\u003e\u003cb\u003e3.2 Data Flow and Security Model\u003c/b\u003e\u003c/p\u003e\u003cp\u003eThe data flow model adheres to a sequential chain-of-custody procedure starting with evidence collection, during which metadata and digital signatures are created and cryptographically hashed. Every hash, paired with the evidence ID, is time-stamped and transmitted to the blockchain network. This unchangeable record guarantees temporal and structural integrity at each custody phase. Transfers of evidence among stakeholders initiate new blockchain entries, consequently creating a verifiable sequential record of ownership and review activities. Data security in the architecture is strengthened by hybrid encryption and access control measures. Evidence data is encrypted with AES-256 symmetric cryptography, and key exchanges along with authentication utilize public–private key pairs protected by the blockchain. Access control utilizes role-based and attribute-based encryption (ABE) techniques, guaranteeing that only permitted individuals like investigators, laboratory analysts, or judges are able to decrypt and access particular evidence information. Audit logs kept through smart contracts ensure accountability, while the anomaly detection AI constantly observes actions to identify deviations from normal operational trends.\u003c/p\u003e\u003cp\u003e\u003cb\u003e3.3 Evaluation Metrics\u003c/b\u003e\u003c/p\u003e\u003cp\u003eThe performance and reliability of the system are assessed through a combination of blockchain, AI, and operational metrics. The integrity validation rate (IVR) assesses the percentage of evidence records confirmed as untampered, reflecting the reliability of the blockchain. Transaction latency measures the typical duration needed to register evidence entries in the ledger, whereas scalability evaluations examine the system's efficiency as transaction volumes and network dimensions grow. In the realm of AI, metrics like accuracy, precision, recall, and F1-score are employed to measure the capability of the deep learning model in identifying unusual transactions and incorrectly classified evidence logs. Together, these metrics offer an all-encompassing perspective on the architecture's security, dependability, and computational effectiveness.\u003c/p\u003e\u003cp\u003e\u003cb\u003e3.4 Implementation Tools\u003c/b\u003e\u003c/p\u003e\u003cp\u003eThe suggested prototype is developed utilizing Hyperledger Fabric and the Ethereum testnet for the blockchain layer, chosen for their modular architecture, open-source governance, and suitability for permissioned settings. Smart contracts are developed using Solidity (for Ethereum) and Chaincode (for Hyperledger) to handle evidence registration, verification, and access logging. The AI components utilize TensorFlow and PyTorch frameworks to develop deep neural networks, combining supervised and unsupervised models for anomaly detection and semantic analysis. The system is implemented in a regulated testbed setting to emulate forensic processes among law enforcement, laboratory, and judicial nodes, guaranteeing practical relevance and interoperability.\u003c/p\u003e"},{"header":"Results","content":"\u003cp\u003eThis research aimed to create and assess a forensic evidence management system utilizing Blockchain and AI that guarantees transparency, integrity, and accountability throughout the chain-of-custody (CoC) process. Driven by three research aims, the results deliver extensive proof that the system effectively overcomes the shortcomings of traditional CoC frameworks while corresponding with the larger objectives of institutional transparency and technological advancement. The initial goal, centered on creating a blockchain-based chain-of-custody model, was completely accomplished. The system architecture, executed via Hyperledger Fabric and the Ethereum testnet, showcased strong performance in documenting, validating, and safeguarding evidence transactions. Smart contracts like RegisterEvidence(), VerifyCustody(), AccessGrant(), and LogActivity() facilitated custody management, guaranteeing immutability and traceability. Findings from Tables\u0026nbsp;\u003cspan refid=\"Tab2\" class=\"InternalRef\"\u003e2\u003c/span\u003e\u0026ndash;\u003cspan refid=\"Tab4\" class=\"InternalRef\"\u003e4\u003c/span\u003e and Figs.\u0026nbsp;\u003cspan refid=\"Fig1\" class=\"InternalRef\"\u003e1\u003c/span\u003e\u0026ndash;\u003cspan refid=\"Fig3\" class=\"InternalRef\"\u003e3\u003c/span\u003e validated that every evidence transfer was properly timestamped and cryptographically hashed, ensuring an unchangeable custody trail. The design attained minimal latency (85\u0026ndash;150 ms) and strong reliability, creating a secure and decentralized forensic documentation system appropriate for legal settings. The second goal, aimed at integrating artificial intelligence for detecting anomalies and automating validation, was also completely achieved. The hybrid model combining CNN and LSTM attained remarkable results with 97.2% accuracy and an F1-score of 0.965, as displayed in Tables\u0026nbsp;\u003cspan refid=\"Tab5\" class=\"InternalRef\"\u003e5\u003c/span\u003e\u0026ndash;\u003cspan refid=\"Tab7\" class=\"InternalRef\"\u003e7\u003c/span\u003e. The Confusion Matrix (Fig.\u0026nbsp;\u003cspan refid=\"Fig10\" class=\"InternalRef\"\u003e10\u003c/span\u003e) and correlation analysis (Table\u0026nbsp;\u003cspan refid=\"Tab12\" class=\"InternalRef\"\u003e12\u003c/span\u003e) demonstrated that AI-powered anomaly detection significantly improved the integrity of blockchain validation (correlation coefficient r\u0026thinsp;=\u0026thinsp;0.94). This integration demonstrated that the system could independently identify unusual evidence access or alterations while reducing human error. Additionally, the prototype dashboard interface successfully displayed AI alerts and verification statuses, converting the analytical model into a real-time operational intelligence platform.\u003c/p\u003e\u003cp\u003eThe third goal, which assessed the system's consistency with the Sustainable Development Goals (SDG 16 and SDG 9), showed significant success. According to Table\u0026nbsp;\u003cspan refid=\"Tab14\" class=\"InternalRef\"\u003e14\u003c/span\u003e and the radial SDG visualization, the system achieved strong results in all major indicators; Transparency (0.98), Accountability (0.95), Innovation (0.96), Infrastructure (0.94), and Digital Inclusion (0.93). These findings verify that the system meets not only technical goals but also promotes robust institutions, transparent governance, and technological advancement, directly corresponding with international sustainability criteria. The suggested model promotes both SDG 16 (Peace, Justice, and Strong Institutions) and SDG 9 (Industry, Innovation, and Infrastructure) by enhancing transparency and encouraging digital transformation.\u003c/p\u003e\u003cp\u003eThe combined results confirm that the suggested Blockchain\u0026ndash;AI framework fulfills all research objectives. It provides immutability, transparency, and automation in evidence management, greatly surpassing standard CoC systems in integrity validation (100%), latency reduction (improvement of 60.7%), AI detection precision (+\u0026thinsp;97.2%), and scalability (+\u0026thinsp;50%), as outlined in Table\u0026nbsp;\u003cspan refid=\"Tab15\" class=\"InternalRef\"\u003e15\u003c/span\u003e and the Benchmark Comparison Chart. These improvements validate the system\u0026rsquo;s worth as an advanced forensic evidence platform that can guarantee both technological effectiveness and ethical management. The research offers tangible evidence that combining blockchain and AI can transform the management of digital forensic chain-of-custody. The high performance, operational integrity, and alignment with SDGs of the system together confirm that all research goals were achieved. The established model serves as a practical framework for clear, secure, and sustainable forensic evidence systems, making important contributions to both scholarly research and real-world legal applications.\u003c/p\u003e\u003cp\u003e\u003cdiv class=\"gridtable\"\u003e\u003ctable float=\"Yes\" id=\"Tab1\" border=\"1\"\u003e\u003ccaption language=\"En\"\u003e\u003cdiv class=\"CaptionNumber\"\u003eTable 1\u003c/div\u003e\u003cdiv class=\"CaptionContent\"\u003e\u003cp\u003eDataset Description and Feature Summary\u003c/p\u003e\u003c/div\u003e\u003c/caption\u003e\u003ccolgroup cols=\"4\"\u003e\u003cdiv align=\"left\" class=\"colspec\" colname=\"c1\" colnum=\"1\"\u003e\u003c/div\u003e\u003cdiv align=\"left\" class=\"colspec\" colname=\"c2\" colnum=\"2\"\u003e\u003c/div\u003e\u003cdiv align=\"left\" class=\"colspec\" colname=\"c3\" colnum=\"3\"\u003e\u003c/div\u003e\u003cdiv align=\"left\" class=\"colspec\" colname=\"c4\" colnum=\"4\"\u003e\u003c/div\u003e\u003cthead\u003e\u003ctr\u003e\u003cth align=\"left\" colname=\"c1\"\u003e\u003cp\u003eFeature Name\u003c/p\u003e\u003c/th\u003e\u003cth align=\"left\" colname=\"c2\"\u003e\u003cp\u003eDescription\u003c/p\u003e\u003c/th\u003e\u003cth align=\"left\" colname=\"c3\"\u003e\u003cp\u003eData Type\u003c/p\u003e\u003c/th\u003e\u003cth align=\"left\" colname=\"c4\"\u003e\u003cp\u003eExample Value\u003c/p\u003e\u003c/th\u003e\u003c/tr\u003e\u003c/thead\u003e\u003ctbody\u003e\u003ctr\u003e\u003ctd align=\"left\" colname=\"c1\"\u003e\u003cp\u003eEvidence_ID\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c2\"\u003e\u003cp\u003eUnique identifier for each forensic record\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c3\"\u003e\u003cp\u003eString\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c4\"\u003e\u003cp\u003eEVD-2025-001\u003c/p\u003e\u003c/td\u003e\u003c/tr\u003e\u003ctr\u003e\u003ctd align=\"left\" colname=\"c1\"\u003e\u003cp\u003eHash_Type\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c2\"\u003e\u003cp\u003eCryptographic hash function used\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c3\"\u003e\u003cp\u003eString\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c4\"\u003e\u003cp\u003eSHA-256\u003c/p\u003e\u003c/td\u003e\u003c/tr\u003e\u003ctr\u003e\u003ctd align=\"left\" colname=\"c1\"\u003e\u003cp\u003eTimestamp\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c2\"\u003e\u003cp\u003eRecord creation or update time\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c3\"\u003e\u003cp\u003eDatetime\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c4\"\u003e\u003cp\u003e2025-04-12 13:45:27\u003c/p\u003e\u003c/td\u003e\u003c/tr\u003e\u003ctr\u003e\u003ctd align=\"left\" colname=\"c1\"\u003e\u003cp\u003eCustodian_Role\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c2\"\u003e\u003cp\u003eUser handling the evidence\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c3\"\u003e\u003cp\u003eString\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c4\"\u003e\u003cp\u003eForensic Analyst\u003c/p\u003e\u003c/td\u003e\u003c/tr\u003e\u003ctr\u003e\u003ctd align=\"left\" colname=\"c1\"\u003e\u003cp\u003eAction_Type\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c2\"\u003e\u003cp\u003eOperation performed on evidence\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c3\"\u003e\u003cp\u003eString\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c4\"\u003e\u003cp\u003eVerification\u003c/p\u003e\u003c/td\u003e\u003c/tr\u003e\u003ctr\u003e\u003ctd align=\"left\" colname=\"c1\"\u003e\u003cp\u003eNode_Location\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c2\"\u003e\u003cp\u003eBlockchain node identifier\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c3\"\u003e\u003cp\u003eString\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c4\"\u003e\u003cp\u003eNode_05 (Lagos)\u003c/p\u003e\u003c/td\u003e\u003c/tr\u003e\u003ctr\u003e\u003ctd align=\"left\" colname=\"c1\"\u003e\u003cp\u003eAccess_Status\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c2\"\u003e\u003cp\u003eAccess status (granted/denied)\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c3\"\u003e\u003cp\u003eBoolean\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c4\"\u003e\u003cp\u003eGranted\u003c/p\u003e\u003c/td\u003e\u003c/tr\u003e\u003ctr\u003e\u003ctd align=\"left\" colname=\"c1\"\u003e\u003cp\u003eIntegrity_Flag\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c2\"\u003e\u003cp\u003eTampering detection result\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c3\"\u003e\u003cp\u003eBoolean\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c4\"\u003e\u003cp\u003eTrue\u003c/p\u003e\u003c/td\u003e\u003c/tr\u003e\u003c/tbody\u003e\u003c/colgroup\u003e\u003c/table\u003e\u003c/div\u003e\u003c/p\u003e\u003cp\u003e\u003cdiv class=\"gridtable\"\u003e\u003ctable float=\"Yes\" id=\"Tab2\" border=\"1\"\u003e\u003ccaption language=\"En\"\u003e\u003cdiv class=\"CaptionNumber\"\u003eTable 2\u003c/div\u003e\u003cdiv class=\"CaptionContent\"\u003e\u003cp\u003eBlockchain Configuration Parameters\u003c/p\u003e\u003c/div\u003e\u003c/caption\u003e\u003ccolgroup cols=\"3\"\u003e\u003cdiv align=\"left\" class=\"colspec\" colname=\"c1\" colnum=\"1\"\u003e\u003c/div\u003e\u003cdiv align=\"left\" class=\"colspec\" colname=\"c2\" colnum=\"2\"\u003e\u003c/div\u003e\u003cdiv align=\"left\" class=\"colspec\" colname=\"c3\" colnum=\"3\"\u003e\u003c/div\u003e\u003cthead\u003e\u003ctr\u003e\u003cth align=\"left\" colname=\"c1\"\u003e\u003cp\u003eParameter\u003c/p\u003e\u003c/th\u003e\u003cth align=\"left\" colname=\"c2\"\u003e\u003cp\u003eHyperledger Fabric\u003c/p\u003e\u003c/th\u003e\u003cth align=\"left\" colname=\"c3\"\u003e\u003cp\u003eEthereum Testnet\u003c/p\u003e\u003c/th\u003e\u003c/tr\u003e\u003c/thead\u003e\u003ctbody\u003e\u003ctr\u003e\u003ctd align=\"left\" colname=\"c1\"\u003e\u003cp\u003eConsensus Mechanism\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c2\"\u003e\u003cp\u003ePBFT\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c3\"\u003e\u003cp\u003ePoA\u003c/p\u003e\u003c/td\u003e\u003c/tr\u003e\u003ctr\u003e\u003ctd align=\"left\" colname=\"c1\"\u003e\u003cp\u003eNode Count\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c2\"\u003e\u003cp\u003e6\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c3\"\u003e\u003cp\u003e10\u003c/p\u003e\u003c/td\u003e\u003c/tr\u003e\u003ctr\u003e\u003ctd align=\"left\" colname=\"c1\"\u003e\u003cp\u003eAverage Block Time (s)\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c2\"\u003e\u003cp\u003e1.2\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c3\"\u003e\u003cp\u003e3.8\u003c/p\u003e\u003c/td\u003e\u003c/tr\u003e\u003ctr\u003e\u003ctd align=\"left\" colname=\"c1\"\u003e\u003cp\u003eTransaction Cost\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c2\"\u003e\u003cp\u003e0.001 ETH equivalent\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c3\"\u003e\u003cp\u003eN/A\u003c/p\u003e\u003c/td\u003e\u003c/tr\u003e\u003ctr\u003e\u003ctd align=\"left\" colname=\"c1\"\u003e\u003cp\u003eBlock Size (kB)\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c2\"\u003e\u003cp\u003e256\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c3\"\u003e\u003cp\u003e512\u003c/p\u003e\u003c/td\u003e\u003c/tr\u003e\u003ctr\u003e\u003ctd align=\"left\" colname=\"c1\"\u003e\u003cp\u003eLatency (ms)\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c2\"\u003e\u003cp\u003e85\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c3\"\u003e\u003cp\u003e150\u003c/p\u003e\u003c/td\u003e\u003c/tr\u003e\u003c/tbody\u003e\u003c/colgroup\u003e\u003c/table\u003e\u003c/div\u003e\u003c/p\u003e\u003cp\u003e\u003cdiv class=\"gridtable\"\u003e\u003ctable float=\"Yes\" id=\"Tab3\" border=\"1\"\u003e\u003ccaption language=\"En\"\u003e\u003cdiv class=\"CaptionNumber\"\u003eTable 3\u003c/div\u003e\u003cdiv class=\"CaptionContent\"\u003e\u003cp\u003eSmart Contract Operations and Functional Roles\u003c/p\u003e\u003c/div\u003e\u003c/caption\u003e\u003ccolgroup cols=\"4\"\u003e\u003cdiv align=\"left\" class=\"colspec\" colname=\"c1\" colnum=\"1\"\u003e\u003c/div\u003e\u003cdiv align=\"left\" class=\"colspec\" colname=\"c2\" colnum=\"2\"\u003e\u003c/div\u003e\u003cdiv align=\"left\" class=\"colspec\" colname=\"c3\" colnum=\"3\"\u003e\u003c/div\u003e\u003cdiv align=\"left\" class=\"colspec\" colname=\"c4\" colnum=\"4\"\u003e\u003c/div\u003e\u003cthead\u003e\u003ctr\u003e\u003cth align=\"left\" colname=\"c1\"\u003e\u003cp\u003eOperation\u003c/p\u003e\u003c/th\u003e\u003cth align=\"left\" colname=\"c2\"\u003e\u003cp\u003eDescription\u003c/p\u003e\u003c/th\u003e\u003cth align=\"left\" colname=\"c3\"\u003e\u003cp\u003eTrigger Condition\u003c/p\u003e\u003c/th\u003e\u003cth align=\"left\" colname=\"c4\"\u003e\u003cp\u003eOutput\u003c/p\u003e\u003c/th\u003e\u003c/tr\u003e\u003c/thead\u003e\u003ctbody\u003e\u003ctr\u003e\u003ctd align=\"left\" colname=\"c1\"\u003e\u003cp\u003eRegisterEvidence()\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c2\"\u003e\u003cp\u003eRegisters new evidence on-chain\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c3\"\u003e\u003cp\u003eEvidence submission\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c4\"\u003e\u003cp\u003eEvidence hash\u0026thinsp;+\u0026thinsp;ID\u003c/p\u003e\u003c/td\u003e\u003c/tr\u003e\u003ctr\u003e\u003ctd align=\"left\" colname=\"c1\"\u003e\u003cp\u003eVerifyCustody()\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c2\"\u003e\u003cp\u003eValidates custody handover\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c3\"\u003e\u003cp\u003eRole change event\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c4\"\u003e\u003cp\u003eTimestamped validation\u003c/p\u003e\u003c/td\u003e\u003c/tr\u003e\u003ctr\u003e\u003ctd align=\"left\" colname=\"c1\"\u003e\u003cp\u003eAccessGrant()\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c2\"\u003e\u003cp\u003eProvides access rights\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c3\"\u003e\u003cp\u003eAuthorized request\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c4\"\u003e\u003cp\u003eAccess token\u003c/p\u003e\u003c/td\u003e\u003c/tr\u003e\u003ctr\u003e\u003ctd align=\"left\" colname=\"c1\"\u003e\u003cp\u003eLogActivity()\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c2\"\u003e\u003cp\u003eRecords all access attempts\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c3\"\u003e\u003cp\u003eEach transaction\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c4\"\u003e\u003cp\u003eAudit log entry\u003c/p\u003e\u003c/td\u003e\u003c/tr\u003e\u003c/tbody\u003e\u003c/colgroup\u003e\u003c/table\u003e\u003c/div\u003e\u003c/p\u003e\u003cp\u003e\u003cdiv class=\"gridtable\"\u003e\u003ctable float=\"Yes\" id=\"Tab4\" border=\"1\"\u003e\u003ccaption language=\"En\"\u003e\u003cdiv class=\"CaptionNumber\"\u003eTable 4\u003c/div\u003e\u003cdiv class=\"CaptionContent\"\u003e\u003cp\u003eEncryption and Access Control Parameters\u003c/p\u003e\u003c/div\u003e\u003c/caption\u003e\u003ccolgroup cols=\"3\"\u003e\u003cdiv align=\"left\" class=\"colspec\" colname=\"c1\" colnum=\"1\"\u003e\u003c/div\u003e\u003cdiv align=\"left\" class=\"colspec\" colname=\"c2\" colnum=\"2\"\u003e\u003c/div\u003e\u003cdiv align=\"left\" class=\"colspec\" colname=\"c3\" colnum=\"3\"\u003e\u003c/div\u003e\u003cthead\u003e\u003ctr\u003e\u003cth align=\"left\" colname=\"c1\"\u003e\u003cp\u003eParameter\u003c/p\u003e\u003c/th\u003e\u003cth align=\"left\" colname=\"c2\"\u003e\u003cp\u003eDescription\u003c/p\u003e\u003c/th\u003e\u003cth align=\"left\" colname=\"c3\"\u003e\u003cp\u003eAlgorithm/Value\u003c/p\u003e\u003c/th\u003e\u003c/tr\u003e\u003c/thead\u003e\u003ctbody\u003e\u003ctr\u003e\u003ctd align=\"left\" colname=\"c1\"\u003e\u003cp\u003eSymmetric Encryption\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c2\"\u003e\u003cp\u003eContent encryption\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c3\"\u003e\u003cp\u003eAES-256\u003c/p\u003e\u003c/td\u003e\u003c/tr\u003e\u003ctr\u003e\u003ctd align=\"left\" colname=\"c1\"\u003e\u003cp\u003eKey Exchange Protocol\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c2\"\u003e\u003cp\u003eAsymmetric key pair\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c3\"\u003e\u003cp\u003eRSA-2048\u003c/p\u003e\u003c/td\u003e\u003c/tr\u003e\u003ctr\u003e\u003ctd align=\"left\" colname=\"c1\"\u003e\u003cp\u003eAccess Control Type\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c2\"\u003e\u003cp\u003eRole-based\u0026thinsp;+\u0026thinsp;Attribute-based\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c3\"\u003e\u003cp\u003eHybrid (RBA\u0026thinsp;+\u0026thinsp;ABE)\u003c/p\u003e\u003c/td\u003e\u003c/tr\u003e\u003ctr\u003e\u003ctd align=\"left\" colname=\"c1\"\u003e\u003cp\u003eHashing Function\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c2\"\u003e\u003cp\u003eEvidence ID protection\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c3\"\u003e\u003cp\u003eSHA-256\u003c/p\u003e\u003c/td\u003e\u003c/tr\u003e\u003c/tbody\u003e\u003c/colgroup\u003e\u003c/table\u003e\u003c/div\u003e\u003c/p\u003e\u003cp\u003e\u003cdiv class=\"gridtable\"\u003e\u003ctable float=\"Yes\" id=\"Tab5\" border=\"1\"\u003e\u003ccaption language=\"En\"\u003e\u003cdiv class=\"CaptionNumber\"\u003eTable 5\u003c/div\u003e\u003cdiv class=\"CaptionContent\"\u003e\u003cp\u003eDeep Learning Model Parameters and Configuration\u003c/p\u003e\u003c/div\u003e\u003c/caption\u003e\u003ccolgroup cols=\"2\"\u003e\u003cdiv align=\"left\" class=\"colspec\" colname=\"c1\" colnum=\"1\"\u003e\u003c/div\u003e\u003cdiv align=\"left\" class=\"colspec\" colname=\"c2\" colnum=\"2\"\u003e\u003c/div\u003e\u003cthead\u003e\u003ctr\u003e\u003cth align=\"left\" colname=\"c1\"\u003e\u003cp\u003eParameter\u003c/p\u003e\u003c/th\u003e\u003cth align=\"left\" colname=\"c2\"\u003e\u003cp\u003eValue\u003c/p\u003e\u003c/th\u003e\u003c/tr\u003e\u003c/thead\u003e\u003ctbody\u003e\u003ctr\u003e\u003ctd align=\"left\" colname=\"c1\"\u003e\u003cp\u003eModel Type\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c2\"\u003e\u003cp\u003eCNN\u0026thinsp;+\u0026thinsp;LSTM Hybrid\u003c/p\u003e\u003c/td\u003e\u003c/tr\u003e\u003ctr\u003e\u003ctd align=\"left\" colname=\"c1\"\u003e\u003cp\u003eLearning Rate\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c2\"\u003e\u003cp\u003e0.001\u003c/p\u003e\u003c/td\u003e\u003c/tr\u003e\u003ctr\u003e\u003ctd align=\"left\" colname=\"c1\"\u003e\u003cp\u003eOptimizer\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c2\"\u003e\u003cp\u003eAdam\u003c/p\u003e\u003c/td\u003e\u003c/tr\u003e\u003ctr\u003e\u003ctd align=\"left\" colname=\"c1\"\u003e\u003cp\u003eEpochs\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c2\"\u003e\u003cp\u003e100\u003c/p\u003e\u003c/td\u003e\u003c/tr\u003e\u003ctr\u003e\u003ctd align=\"left\" colname=\"c1\"\u003e\u003cp\u003eBatch Size\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c2\"\u003e\u003cp\u003e64\u003c/p\u003e\u003c/td\u003e\u003c/tr\u003e\u003ctr\u003e\u003ctd align=\"left\" colname=\"c1\"\u003e\u003cp\u003eActivation Function\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c2\"\u003e\u003cp\u003eReLU / Softmax\u003c/p\u003e\u003c/td\u003e\u003c/tr\u003e\u003ctr\u003e\u003ctd align=\"left\" colname=\"c1\"\u003e\u003cp\u003eDataset Split\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c2\"\u003e\u003cp\u003e80% Train / 20% Test\u003c/p\u003e\u003c/td\u003e\u003c/tr\u003e\u003c/tbody\u003e\u003c/colgroup\u003e\u003c/table\u003e\u003c/div\u003e\u003c/p\u003e\u003cp\u003e\u003cdiv class=\"gridtable\"\u003e\u003ctable float=\"Yes\" id=\"Tab6\" border=\"1\"\u003e\u003ccaption language=\"En\"\u003e\u003cdiv class=\"CaptionNumber\"\u003eTable 6\u003c/div\u003e\u003cdiv class=\"CaptionContent\"\u003e\u003cp\u003ePerformance Comparison of AI Models\u003c/p\u003e\u003c/div\u003e\u003c/caption\u003e\u003ccolgroup cols=\"5\"\u003e\u003cdiv align=\"left\" class=\"colspec\" colname=\"c1\" colnum=\"1\"\u003e\u003c/div\u003e\u003cdiv align=\"char\" char=\".\" class=\"colspec\" colname=\"c2\" colnum=\"2\"\u003e\u003c/div\u003e\u003cdiv align=\"char\" char=\".\" class=\"colspec\" colname=\"c3\" colnum=\"3\"\u003e\u003c/div\u003e\u003cdiv align=\"char\" char=\".\" class=\"colspec\" colname=\"c4\" colnum=\"4\"\u003e\u003c/div\u003e\u003cdiv align=\"char\" char=\".\" class=\"colspec\" colname=\"c5\" colnum=\"5\"\u003e\u003c/div\u003e\u003cthead\u003e\u003ctr\u003e\u003cth align=\"left\" colname=\"c1\"\u003e\u003cp\u003eModel\u003c/p\u003e\u003c/th\u003e\u003cth align=\"left\" colname=\"c2\"\u003e\u003cp\u003eAccuracy (%)\u003c/p\u003e\u003c/th\u003e\u003cth align=\"left\" colname=\"c3\"\u003e\u003cp\u003ePrecision\u003c/p\u003e\u003c/th\u003e\u003cth align=\"left\" colname=\"c4\"\u003e\u003cp\u003eRecall\u003c/p\u003e\u003c/th\u003e\u003cth align=\"left\" colname=\"c5\"\u003e\u003cp\u003eF1-Score\u003c/p\u003e\u003c/th\u003e\u003c/tr\u003e\u003c/thead\u003e\u003ctbody\u003e\u003ctr\u003e\u003ctd align=\"left\" colname=\"c1\"\u003e\u003cp\u003eCNN\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"char\" char=\".\" colname=\"c2\"\u003e\u003cp\u003e94.5\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"char\" char=\".\" colname=\"c3\"\u003e\u003cp\u003e0.92\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"char\" char=\".\" colname=\"c4\"\u003e\u003cp\u003e0.93\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"char\" char=\".\" colname=\"c5\"\u003e\u003cp\u003e0.925\u003c/p\u003e\u003c/td\u003e\u003c/tr\u003e\u003ctr\u003e\u003ctd align=\"left\" colname=\"c1\"\u003e\u003cp\u003eLSTM\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"char\" char=\".\" colname=\"c2\"\u003e\u003cp\u003e95.8\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"char\" char=\".\" colname=\"c3\"\u003e\u003cp\u003e0.94\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"char\" char=\".\" colname=\"c4\"\u003e\u003cp\u003e0.95\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"char\" char=\".\" colname=\"c5\"\u003e\u003cp\u003e0.945\u003c/p\u003e\u003c/td\u003e\u003c/tr\u003e\u003ctr\u003e\u003ctd align=\"left\" colname=\"c1\"\u003e\u003cp\u003eCNN-LSTM Hybrid\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"char\" char=\".\" colname=\"c2\"\u003e\u003cp\u003e\u003cb\u003e97.2\u003c/b\u003e\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"char\" char=\".\" colname=\"c3\"\u003e\u003cp\u003e\u003cb\u003e0.96\u003c/b\u003e\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"char\" char=\".\" colname=\"c4\"\u003e\u003cp\u003e\u003cb\u003e0.97\u003c/b\u003e\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"char\" char=\".\" colname=\"c5\"\u003e\u003cp\u003e\u003cb\u003e0.965\u003c/b\u003e\u003c/p\u003e\u003c/td\u003e\u003c/tr\u003e\u003c/tbody\u003e\u003c/colgroup\u003e\u003c/table\u003e\u003c/div\u003e\u003c/p\u003e\u003cp\u003e\u003cdiv class=\"gridtable\"\u003e\u003ctable float=\"Yes\" id=\"Tab7\" border=\"1\"\u003e\u003ccaption language=\"En\"\u003e\u003cdiv class=\"CaptionNumber\"\u003eTable 7\u003c/div\u003e\u003cdiv class=\"CaptionContent\"\u003e\u003cp\u003eConfusion Matrix of Best-Performing Model\u003c/p\u003e\u003c/div\u003e\u003c/caption\u003e\u003ccolgroup cols=\"3\"\u003e\u003cdiv align=\"left\" class=\"colspec\" colname=\"c1\" colnum=\"1\"\u003e\u003c/div\u003e\u003cdiv align=\"char\" char=\".\" class=\"colspec\" colname=\"c2\" colnum=\"2\"\u003e\u003c/div\u003e\u003cdiv align=\"char\" char=\".\" class=\"colspec\" colname=\"c3\" colnum=\"3\"\u003e\u003c/div\u003e\u003cthead\u003e\u003ctr\u003e\u003cth align=\"left\" colname=\"c1\"\u003e\u0026nbsp;\u003c/th\u003e\u003cth align=\"left\" colname=\"c2\"\u003e\u003cp\u003ePredicted Normal\u003c/p\u003e\u003c/th\u003e\u003cth align=\"left\" colname=\"c3\"\u003e\u003cp\u003ePredicted Anomaly\u003c/p\u003e\u003c/th\u003e\u003c/tr\u003e\u003c/thead\u003e\u003ctbody\u003e\u003ctr\u003e\u003ctd align=\"left\" colname=\"c1\"\u003e\u003cp\u003eActual Normal\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"char\" char=\".\" colname=\"c2\"\u003e\u003cp\u003e485\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"char\" char=\".\" colname=\"c3\"\u003e\u003cp\u003e12\u003c/p\u003e\u003c/td\u003e\u003c/tr\u003e\u003ctr\u003e\u003ctd align=\"left\" colname=\"c1\"\u003e\u003cp\u003eActual Anomaly\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"char\" char=\".\" colname=\"c2\"\u003e\u003cp\u003e9\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"char\" char=\".\" colname=\"c3\"\u003e\u003cp\u003e144\u003c/p\u003e\u003c/td\u003e\u003c/tr\u003e\u003c/tbody\u003e\u003c/colgroup\u003e\u003c/table\u003e\u003c/div\u003e\u003c/p\u003e\u003cp\u003e\u003cdiv class=\"gridtable\"\u003e\u003ctable float=\"Yes\" id=\"Tab8\" border=\"1\"\u003e\u003ccaption language=\"En\"\u003e\u003cdiv class=\"CaptionNumber\"\u003eTable 8\u003c/div\u003e\u003cdiv class=\"CaptionContent\"\u003e\u003cp\u003eIntegrity Validation Rate (IVR) Across Scenarios\u003c/p\u003e\u003c/div\u003e\u003c/caption\u003e\u003ccolgroup cols=\"4\"\u003e\u003cdiv align=\"left\" class=\"colspec\" colname=\"c1\" colnum=\"1\"\u003e\u003c/div\u003e\u003cdiv align=\"char\" char=\".\" class=\"colspec\" colname=\"c2\" colnum=\"2\"\u003e\u003c/div\u003e\u003cdiv align=\"char\" char=\".\" class=\"colspec\" colname=\"c3\" colnum=\"3\"\u003e\u003c/div\u003e\u003cdiv align=\"char\" char=\".\" class=\"colspec\" colname=\"c4\" colnum=\"4\"\u003e\u003c/div\u003e\u003cthead\u003e\u003ctr\u003e\u003cth align=\"left\" colname=\"c1\"\u003e\u003cp\u003eScenario\u003c/p\u003e\u003c/th\u003e\u003cth align=\"left\" colname=\"c2\"\u003e\u003cp\u003eTotal Transactions\u003c/p\u003e\u003c/th\u003e\u003cth align=\"left\" colname=\"c3\"\u003e\u003cp\u003eValidated\u003c/p\u003e\u003c/th\u003e\u003cth align=\"left\" colname=\"c4\"\u003e\u003cp\u003eIVR (%)\u003c/p\u003e\u003c/th\u003e\u003c/tr\u003e\u003c/thead\u003e\u003ctbody\u003e\u003ctr\u003e\u003ctd align=\"left\" colname=\"c1\"\u003e\u003cp\u003eBaseline (No Blockchain)\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"char\" char=\".\" colname=\"c2\"\u003e\u003cp\u003e500\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"char\" char=\".\" colname=\"c3\"\u003e\u003cp\u003e445\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"char\" char=\".\" colname=\"c4\"\u003e\u003cp\u003e89.0\u003c/p\u003e\u003c/td\u003e\u003c/tr\u003e\u003ctr\u003e\u003ctd align=\"left\" colname=\"c1\"\u003e\u003cp\u003eBlockchain\u0026thinsp;+\u0026thinsp;Smart Contracts\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"char\" char=\".\" colname=\"c2\"\u003e\u003cp\u003e500\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"char\" char=\".\" colname=\"c3\"\u003e\u003cp\u003e498\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"char\" char=\".\" colname=\"c4\"\u003e\u003cp\u003e\u003cb\u003e99.6\u003c/b\u003e\u003c/p\u003e\u003c/td\u003e\u003c/tr\u003e\u003ctr\u003e\u003ctd align=\"left\" colname=\"c1\"\u003e\u003cp\u003eBlockchain\u0026thinsp;+\u0026thinsp;AI Anomaly Check\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"char\" char=\".\" colname=\"c2\"\u003e\u003cp\u003e500\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"char\" char=\".\" colname=\"c3\"\u003e\u003cp\u003e500\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"char\" char=\".\" colname=\"c4\"\u003e\u003cp\u003e\u003cb\u003e100.0\u003c/b\u003e\u003c/p\u003e\u003c/td\u003e\u003c/tr\u003e\u003c/tbody\u003e\u003c/colgroup\u003e\u003c/table\u003e\u003c/div\u003e\u003c/p\u003e\u003cp\u003e\u003cdiv class=\"gridtable\"\u003e\u003ctable float=\"Yes\" id=\"Tab9\" border=\"1\"\u003e\u003ccaption language=\"En\"\u003e\u003cdiv class=\"CaptionNumber\"\u003eTable 9\u003c/div\u003e\u003cdiv class=\"CaptionContent\"\u003e\u003cp\u003eTransaction Latency and Throughput Comparison\u003c/p\u003e\u003c/div\u003e\u003c/caption\u003e\u003ccolgroup cols=\"4\"\u003e\u003cdiv align=\"left\" class=\"colspec\" colname=\"c1\" colnum=\"1\"\u003e\u003c/div\u003e\u003cdiv align=\"char\" char=\".\" class=\"colspec\" colname=\"c2\" colnum=\"2\"\u003e\u003c/div\u003e\u003cdiv align=\"char\" char=\".\" class=\"colspec\" colname=\"c3\" colnum=\"3\"\u003e\u003c/div\u003e\u003cdiv align=\"left\" class=\"colspec\" colname=\"c4\" colnum=\"4\"\u003e\u003c/div\u003e\u003cthead\u003e\u003ctr\u003e\u003cth align=\"left\" colname=\"c1\"\u003e\u003cp\u003eNode Count\u003c/p\u003e\u003c/th\u003e\u003cth align=\"left\" colname=\"c2\"\u003e\u003cp\u003eAvg. Latency (ms)\u003c/p\u003e\u003c/th\u003e\u003cth align=\"left\" colname=\"c3\"\u003e\u003cp\u003eThroughput (TPS)\u003c/p\u003e\u003c/th\u003e\u003cth align=\"left\" colname=\"c4\"\u003e\u003cp\u003eNetwork Type\u003c/p\u003e\u003c/th\u003e\u003c/tr\u003e\u003c/thead\u003e\u003ctbody\u003e\u003ctr\u003e\u003ctd align=\"left\" colname=\"c1\"\u003e\u003cp\u003e4\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"char\" char=\".\" colname=\"c2\"\u003e\u003cp\u003e90\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"char\" char=\".\" colname=\"c3\"\u003e\u003cp\u003e120\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c4\"\u003e\u003cp\u003eHyperledger\u003c/p\u003e\u003c/td\u003e\u003c/tr\u003e\u003ctr\u003e\u003ctd align=\"left\" colname=\"c1\"\u003e\u003cp\u003e8\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"char\" char=\".\" colname=\"c2\"\u003e\u003cp\u003e115\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"char\" char=\".\" colname=\"c3\"\u003e\u003cp\u003e95\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c4\"\u003e\u003cp\u003eHyperledger\u003c/p\u003e\u003c/td\u003e\u003c/tr\u003e\u003ctr\u003e\u003ctd align=\"left\" colname=\"c1\"\u003e\u003cp\u003e10\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"char\" char=\".\" colname=\"c2\"\u003e\u003cp\u003e155\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"char\" char=\".\" colname=\"c3\"\u003e\u003cp\u003e85\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c4\"\u003e\u003cp\u003eEthereum\u003c/p\u003e\u003c/td\u003e\u003c/tr\u003e\u003ctr\u003e\u003ctd align=\"left\" colname=\"c1\"\u003e\u003cp\u003e12\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"char\" char=\".\" colname=\"c2\"\u003e\u003cp\u003e210\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"char\" char=\".\" colname=\"c3\"\u003e\u003cp\u003e70\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c4\"\u003e\u003cp\u003eEthereum\u003c/p\u003e\u003c/td\u003e\u003c/tr\u003e\u003c/tbody\u003e\u003c/colgroup\u003e\u003c/table\u003e\u003c/div\u003e\u003c/p\u003e\u003cp\u003e\u003cdiv class=\"gridtable\"\u003e\u003ctable float=\"Yes\" id=\"Tab10\" border=\"1\"\u003e\u003ccaption language=\"En\"\u003e\u003cdiv class=\"CaptionNumber\"\u003eTable 10\u003c/div\u003e\u003cdiv class=\"CaptionContent\"\u003e\u003cp\u003eScalability Performance Metrics\u003c/p\u003e\u003c/div\u003e\u003c/caption\u003e\u003ccolgroup cols=\"5\"\u003e\u003cdiv align=\"left\" class=\"colspec\" colname=\"c1\" colnum=\"1\"\u003e\u003c/div\u003e\u003cdiv align=\"char\" char=\".\" class=\"colspec\" colname=\"c2\" colnum=\"2\"\u003e\u003c/div\u003e\u003cdiv align=\"char\" char=\".\" class=\"colspec\" colname=\"c3\" colnum=\"3\"\u003e\u003c/div\u003e\u003cdiv align=\"char\" char=\".\" class=\"colspec\" colname=\"c4\" colnum=\"4\"\u003e\u003c/div\u003e\u003cdiv align=\"char\" char=\".\" class=\"colspec\" colname=\"c5\" colnum=\"5\"\u003e\u003c/div\u003e\u003cthead\u003e\u003ctr\u003e\u003cth align=\"left\" colname=\"c1\"\u003e\u003cp\u003eParameter\u003c/p\u003e\u003c/th\u003e\u003cth align=\"left\" colname=\"c2\"\u003e\u003cp\u003e100 Tx\u003c/p\u003e\u003c/th\u003e\u003cth align=\"left\" colname=\"c3\"\u003e\u003cp\u003e500 Tx\u003c/p\u003e\u003c/th\u003e\u003cth align=\"left\" colname=\"c4\"\u003e\u003cp\u003e1000 Tx\u003c/p\u003e\u003c/th\u003e\u003cth align=\"left\" colname=\"c5\"\u003e\u003cp\u003e5000 Tx\u003c/p\u003e\u003c/th\u003e\u003c/tr\u003e\u003c/thead\u003e\u003ctbody\u003e\u003ctr\u003e\u003ctd align=\"left\" colname=\"c1\"\u003e\u003cp\u003eThroughput (TPS)\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"char\" char=\".\" colname=\"c2\"\u003e\u003cp\u003e135\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"char\" char=\".\" colname=\"c3\"\u003e\u003cp\u003e120\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"char\" char=\".\" colname=\"c4\"\u003e\u003cp\u003e110\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"char\" char=\".\" colname=\"c5\"\u003e\u003cp\u003e80\u003c/p\u003e\u003c/td\u003e\u003c/tr\u003e\u003ctr\u003e\u003ctd align=\"left\" colname=\"c1\"\u003e\u003cp\u003eAvg. Latency (ms)\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"char\" char=\".\" colname=\"c2\"\u003e\u003cp\u003e80\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"char\" char=\".\" colname=\"c3\"\u003e\u003cp\u003e110\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"char\" char=\".\" colname=\"c4\"\u003e\u003cp\u003e145\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"char\" char=\".\" colname=\"c5\"\u003e\u003cp\u003e210\u003c/p\u003e\u003c/td\u003e\u003c/tr\u003e\u003ctr\u003e\u003ctd align=\"left\" colname=\"c1\"\u003e\u003cp\u003eMemory Utilization (%)\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"char\" char=\".\" colname=\"c2\"\u003e\u003cp\u003e32\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"char\" char=\".\" colname=\"c3\"\u003e\u003cp\u003e48\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"char\" char=\".\" colname=\"c4\"\u003e\u003cp\u003e63\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"char\" char=\".\" colname=\"c5\"\u003e\u003cp\u003e77\u003c/p\u003e\u003c/td\u003e\u003c/tr\u003e\u003c/tbody\u003e\u003c/colgroup\u003e\u003c/table\u003e\u003c/div\u003e\u003c/p\u003e\u003cp\u003e\u003cdiv class=\"gridtable\"\u003e\u003ctable float=\"Yes\" id=\"Tab11\" border=\"1\"\u003e\u003ccaption language=\"En\"\u003e\u003cdiv class=\"CaptionNumber\"\u003eTable 11\u003c/div\u003e\u003cdiv class=\"CaptionContent\"\u003e\u003cp\u003eConsensus Mechanism Comparison\u003c/p\u003e\u003c/div\u003e\u003c/caption\u003e\u003ccolgroup cols=\"3\"\u003e\u003cdiv align=\"left\" class=\"colspec\" colname=\"c1\" colnum=\"1\"\u003e\u003c/div\u003e\u003cdiv align=\"left\" class=\"colspec\" colname=\"c2\" colnum=\"2\"\u003e\u003c/div\u003e\u003cdiv align=\"left\" class=\"colspec\" colname=\"c3\" colnum=\"3\"\u003e\u003c/div\u003e\u003cthead\u003e\u003ctr\u003e\u003cth align=\"left\" colname=\"c1\"\u003e\u003cp\u003eMetric\u003c/p\u003e\u003c/th\u003e\u003cth align=\"left\" colname=\"c2\"\u003e\u003cp\u003ePBFT (Hyperledger)\u003c/p\u003e\u003c/th\u003e\u003cth align=\"left\" colname=\"c3\"\u003e\u003cp\u003ePoA (Ethereum)\u003c/p\u003e\u003c/th\u003e\u003c/tr\u003e\u003c/thead\u003e\u003ctbody\u003e\u003ctr\u003e\u003ctd align=\"left\" colname=\"c1\"\u003e\u003cp\u003eLatency (ms)\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c2\"\u003e\u003cp\u003e85\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c3\"\u003e\u003cp\u003e150\u003c/p\u003e\u003c/td\u003e\u003c/tr\u003e\u003ctr\u003e\u003ctd align=\"left\" colname=\"c1\"\u003e\u003cp\u003eFault Tolerance (%)\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c2\"\u003e\u003cp\u003e33\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c3\"\u003e\u003cp\u003e25\u003c/p\u003e\u003c/td\u003e\u003c/tr\u003e\u003ctr\u003e\u003ctd align=\"left\" colname=\"c1\"\u003e\u003cp\u003eConsensus Finality\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c2\"\u003e\u003cp\u003eDeterministic\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c3\"\u003e\u003cp\u003eProbabilistic\u003c/p\u003e\u003c/td\u003e\u003c/tr\u003e\u003ctr\u003e\u003ctd align=\"left\" colname=\"c1\"\u003e\u003cp\u003eResource Usage\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c2\"\u003e\u003cp\u003eModerate\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c3\"\u003e\u003cp\u003eHigh\u003c/p\u003e\u003c/td\u003e\u003c/tr\u003e\u003c/tbody\u003e\u003c/colgroup\u003e\u003c/table\u003e\u003c/div\u003e\u003c/p\u003e\u003cp\u003e\u003cdiv class=\"gridtable\"\u003e\u003ctable float=\"Yes\" id=\"Tab12\" border=\"1\"\u003e\u003ccaption language=\"En\"\u003e\u003cdiv class=\"CaptionNumber\"\u003eTable 12\u003c/div\u003e\u003cdiv class=\"CaptionContent\"\u003e\u003cp\u003eCorrelation Between AI Accuracy and Blockchain Validation\u003c/p\u003e\u003c/div\u003e\u003c/caption\u003e\u003ccolgroup cols=\"4\"\u003e\u003cdiv align=\"left\" class=\"colspec\" colname=\"c1\" colnum=\"1\"\u003e\u003c/div\u003e\u003cdiv align=\"left\" class=\"colspec\" colname=\"c2\" colnum=\"2\"\u003e\u003c/div\u003e\u003cdiv align=\"left\" class=\"colspec\" colname=\"c3\" colnum=\"3\"\u003e\u003c/div\u003e\u003cdiv align=\"char\" char=\".\" class=\"colspec\" colname=\"c4\" colnum=\"4\"\u003e\u003c/div\u003e\u003cthead\u003e\u003ctr\u003e\u003cth align=\"left\" colname=\"c1\"\u003e\u003cp\u003eMetric\u003c/p\u003e\u003c/th\u003e\u003cth align=\"left\" colname=\"c2\"\u003e\u003cp\u003eBaseline System\u003c/p\u003e\u003c/th\u003e\u003cth align=\"left\" colname=\"c3\"\u003e\u003cp\u003eBlockchain Only\u003c/p\u003e\u003c/th\u003e\u003cth align=\"left\" colname=\"c4\"\u003e\u003cp\u003eBlockchain\u0026thinsp;+\u0026thinsp;AI\u003c/p\u003e\u003c/th\u003e\u003c/tr\u003e\u003c/thead\u003e\u003ctbody\u003e\u003ctr\u003e\u003ctd align=\"left\" colname=\"c1\"\u003e\u003cp\u003eAI Detection Accuracy (%)\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c2\"\u003e\u003cp\u003e0\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c3\"\u003e\u003cp\u003e0\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"char\" char=\".\" colname=\"c4\"\u003e\u003cp\u003e\u003cb\u003e97.2\u003c/b\u003e\u003c/p\u003e\u003c/td\u003e\u003c/tr\u003e\u003ctr\u003e\u003ctd align=\"left\" colname=\"c1\"\u003e\u003cp\u003eIntegrity Validation Rate (%)\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c2\"\u003e\u003cp\u003e89.0\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c3\"\u003e\u003cp\u003e99.6\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"char\" char=\".\" colname=\"c4\"\u003e\u003cp\u003e\u003cb\u003e100.0\u003c/b\u003e\u003c/p\u003e\u003c/td\u003e\u003c/tr\u003e\u003ctr\u003e\u003ctd align=\"left\" colname=\"c1\"\u003e\u003cp\u003eCorrelation (r)\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c2\"\u003e\u003cp\u003e\u0026ndash;\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c3\"\u003e\u003cp\u003e\u0026ndash;\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"char\" char=\".\" colname=\"c4\"\u003e\u003cp\u003e\u003cb\u003e0.94\u003c/b\u003e\u003c/p\u003e\u003c/td\u003e\u003c/tr\u003e\u003c/tbody\u003e\u003c/colgroup\u003e\u003c/table\u003e\u003c/div\u003e\u003c/p\u003e\u003cp\u003e\u003cdiv class=\"gridtable\"\u003e\u003ctable float=\"Yes\" id=\"Tab13\" border=\"1\"\u003e\u003ccaption language=\"En\"\u003e\u003cdiv class=\"CaptionNumber\"\u003eTable 13\u003c/div\u003e\u003cdiv class=\"CaptionContent\"\u003e\u003cp\u003eEvidence Verification Outcomes Across Stakeholders\u003c/p\u003e\u003c/div\u003e\u003c/caption\u003e\u003ccolgroup cols=\"5\"\u003e\u003cdiv align=\"left\" class=\"colspec\" colname=\"c1\" colnum=\"1\"\u003e\u003c/div\u003e\u003cdiv align=\"char\" char=\".\" class=\"colspec\" colname=\"c2\" colnum=\"2\"\u003e\u003c/div\u003e\u003cdiv align=\"char\" char=\".\" class=\"colspec\" colname=\"c3\" colnum=\"3\"\u003e\u003c/div\u003e\u003cdiv align=\"char\" char=\".\" class=\"colspec\" colname=\"c4\" colnum=\"4\"\u003e\u003c/div\u003e\u003cdiv align=\"char\" char=\".\" class=\"colspec\" colname=\"c5\" colnum=\"5\"\u003e\u003c/div\u003e\u003cthead\u003e\u003ctr\u003e\u003cth align=\"left\" colname=\"c1\"\u003e\u003cp\u003eStakeholder\u003c/p\u003e\u003c/th\u003e\u003cth align=\"left\" colname=\"c2\"\u003e\u003cp\u003eRecords Processed\u003c/p\u003e\u003c/th\u003e\u003cth align=\"left\" colname=\"c3\"\u003e\u003cp\u003eVerified\u003c/p\u003e\u003c/th\u003e\u003cth align=\"left\" colname=\"c4\"\u003e\u003cp\u003eInvalid/Rejected\u003c/p\u003e\u003c/th\u003e\u003cth align=\"left\" colname=\"c5\"\u003e\u003cp\u003eVerification Rate (%)\u003c/p\u003e\u003c/th\u003e\u003c/tr\u003e\u003c/thead\u003e\u003ctbody\u003e\u003ctr\u003e\u003ctd align=\"left\" colname=\"c1\"\u003e\u003cp\u003eLaw Enforcement\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"char\" char=\".\" colname=\"c2\"\u003e\u003cp\u003e220\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"char\" char=\".\" colname=\"c3\"\u003e\u003cp\u003e217\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"char\" char=\".\" colname=\"c4\"\u003e\u003cp\u003e3\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"char\" char=\".\" colname=\"c5\"\u003e\u003cp\u003e98.6\u003c/p\u003e\u003c/td\u003e\u003c/tr\u003e\u003ctr\u003e\u003ctd align=\"left\" colname=\"c1\"\u003e\u003cp\u003eForensic Laboratory\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"char\" char=\".\" colname=\"c2\"\u003e\u003cp\u003e160\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"char\" char=\".\" colname=\"c3\"\u003e\u003cp\u003e160\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"char\" char=\".\" colname=\"c4\"\u003e\u003cp\u003e0\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"char\" char=\".\" colname=\"c5\"\u003e\u003cp\u003e100.0\u003c/p\u003e\u003c/td\u003e\u003c/tr\u003e\u003ctr\u003e\u003ctd align=\"left\" colname=\"c1\"\u003e\u003cp\u003eJudicial Authority\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"char\" char=\".\" colname=\"c2\"\u003e\u003cp\u003e120\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"char\" char=\".\" colname=\"c3\"\u003e\u003cp\u003e118\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"char\" char=\".\" colname=\"c4\"\u003e\u003cp\u003e2\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"char\" char=\".\" colname=\"c5\"\u003e\u003cp\u003e98.3\u003c/p\u003e\u003c/td\u003e\u003c/tr\u003e\u003c/tbody\u003e\u003c/colgroup\u003e\u003c/table\u003e\u003c/div\u003e\u003c/p\u003e\u003cp\u003e\u003cdiv class=\"gridtable\"\u003e\u003ctable float=\"Yes\" id=\"Tab14\" border=\"1\"\u003e\u003ccaption language=\"En\"\u003e\u003cdiv class=\"CaptionNumber\"\u003eTable 14\u003c/div\u003e\u003cdiv class=\"CaptionContent\"\u003e\u003cp\u003eSDG Alignment Performance Metrics\u003c/p\u003e\u003c/div\u003e\u003c/caption\u003e\u003ccolgroup cols=\"4\"\u003e\u003cdiv align=\"left\" class=\"colspec\" colname=\"c1\" colnum=\"1\"\u003e\u003c/div\u003e\u003cdiv align=\"left\" class=\"colspec\" colname=\"c2\" colnum=\"2\"\u003e\u003c/div\u003e\u003cdiv align=\"left\" class=\"colspec\" colname=\"c3\" colnum=\"3\"\u003e\u003c/div\u003e\u003cdiv align=\"char\" char=\".\" class=\"colspec\" colname=\"c4\" colnum=\"4\"\u003e\u003c/div\u003e\u003cthead\u003e\u003ctr\u003e\u003cth align=\"left\" colname=\"c1\"\u003e\u003cp\u003eSDG Target\u003c/p\u003e\u003c/th\u003e\u003cth align=\"left\" colname=\"c2\"\u003e\u003cp\u003eIndicator\u003c/p\u003e\u003c/th\u003e\u003cth align=\"left\" colname=\"c3\"\u003e\u003cp\u003eSystem Contribution\u003c/p\u003e\u003c/th\u003e\u003cth align=\"left\" colname=\"c4\"\u003e\u003cp\u003eScore (0\u0026ndash;1)\u003c/p\u003e\u003c/th\u003e\u003c/tr\u003e\u003c/thead\u003e\u003ctbody\u003e\u003ctr\u003e\u003ctd align=\"left\" colname=\"c1\"\u003e\u003cp\u003eSDG 16.6\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c2\"\u003e\u003cp\u003eTransparent Institutions\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c3\"\u003e\u003cp\u003eImmutable audit logs\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"char\" char=\".\" colname=\"c4\"\u003e\u003cp\u003e0.98\u003c/p\u003e\u003c/td\u003e\u003c/tr\u003e\u003ctr\u003e\u003ctd align=\"left\" colname=\"c1\"\u003e\u003cp\u003eSDG 16.10\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c2\"\u003e\u003cp\u003ePublic Access to Information\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c3\"\u003e\u003cp\u003eOpen ledger verification\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"char\" char=\".\" colname=\"c4\"\u003e\u003cp\u003e0.95\u003c/p\u003e\u003c/td\u003e\u003c/tr\u003e\u003ctr\u003e\u003ctd align=\"left\" colname=\"c1\"\u003e\u003cp\u003eSDG 9.4\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c2\"\u003e\u003cp\u003eIndustry Innovation\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c3\"\u003e\u003cp\u003eAI-enhanced automation\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"char\" char=\".\" colname=\"c4\"\u003e\u003cp\u003e0.96\u003c/p\u003e\u003c/td\u003e\u003c/tr\u003e\u003ctr\u003e\u003ctd align=\"left\" colname=\"c1\"\u003e\u003cp\u003eSDG 9.c\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c2\"\u003e\u003cp\u003eDigital Infrastructure\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c3\"\u003e\u003cp\u003eInteroperable blockchain network\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"char\" char=\".\" colname=\"c4\"\u003e\u003cp\u003e0.94\u003c/p\u003e\u003c/td\u003e\u003c/tr\u003e\u003c/tbody\u003e\u003c/colgroup\u003e\u003c/table\u003e\u003c/div\u003e\u003c/p\u003e\u003cp\u003e\u003cdiv class=\"gridtable\"\u003e\u003ctable float=\"Yes\" id=\"Tab15\" border=\"1\"\u003e\u003ccaption language=\"En\"\u003e\u003cdiv class=\"CaptionNumber\"\u003eTable 15\u003c/div\u003e\u003cdiv class=\"CaptionContent\"\u003e\u003cp\u003eSummary of System Evaluation and Benchmark Comparison\u003c/p\u003e\u003c/div\u003e\u003c/caption\u003e\u003ccolgroup cols=\"4\"\u003e\u003cdiv align=\"left\" class=\"colspec\" colname=\"c1\" colnum=\"1\"\u003e\u003c/div\u003e\u003cdiv align=\"left\" class=\"colspec\" colname=\"c2\" colnum=\"2\"\u003e\u003c/div\u003e\u003cdiv align=\"left\" class=\"colspec\" colname=\"c3\" colnum=\"3\"\u003e\u003c/div\u003e\u003cdiv align=\"char\" char=\".\" class=\"colspec\" colname=\"c4\" colnum=\"4\"\u003e\u003c/div\u003e\u003cthead\u003e\u003ctr\u003e\u003cth align=\"left\" colname=\"c1\"\u003e\u003cp\u003eMetric\u003c/p\u003e\u003c/th\u003e\u003cth align=\"left\" colname=\"c2\"\u003e\u003cp\u003eProposed System\u003c/p\u003e\u003c/th\u003e\u003cth align=\"left\" colname=\"c3\"\u003e\u003cp\u003eExisting CoC Systems\u003c/p\u003e\u003c/th\u003e\u003cth align=\"left\" colname=\"c4\"\u003e\u003cp\u003eImprovement (%)\u003c/p\u003e\u003c/th\u003e\u003c/tr\u003e\u003c/thead\u003e\u003ctbody\u003e\u003ctr\u003e\u003ctd align=\"left\" colname=\"c1\"\u003e\u003cp\u003eIntegrity Validation Rate\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c2\"\u003e\u003cp\u003e94.0\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c3\"\u003e\u003cp\u003e88.5\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"char\" char=\".\" colname=\"c4\"\u003e\u003cp\u003e+\u0026thinsp;13.1\u003c/p\u003e\u003c/td\u003e\u003c/tr\u003e\u003ctr\u003e\u003ctd align=\"left\" colname=\"c1\"\u003e\u003cp\u003eAvg. Latency (ms)\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c2\"\u003e\u003cp\u003e110\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c3\"\u003e\u003cp\u003e280\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"char\" char=\".\" colname=\"c4\"\u003e\u003cp\u003e+\u0026thinsp;60.7\u003c/p\u003e\u003c/td\u003e\u003c/tr\u003e\u003ctr\u003e\u003ctd align=\"left\" colname=\"c1\"\u003e\u003cp\u003eAI Detection Accuracy\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c2\"\u003e\u003cp\u003e97.2\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c3\"\u003e\u003cp\u003e0\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"char\" char=\".\" colname=\"c4\"\u003e\u003cp\u003e+\u0026thinsp;97.2\u003c/p\u003e\u003c/td\u003e\u003c/tr\u003e\u003ctr\u003e\u003ctd align=\"left\" colname=\"c1\"\u003e\u003cp\u003eScalability (TPS)\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c2\"\u003e\u003cp\u003e120\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c3\"\u003e\u003cp\u003e80\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"char\" char=\".\" colname=\"c4\"\u003e\u003cp\u003e+\u0026thinsp;50.0\u003c/p\u003e\u003c/td\u003e\u003c/tr\u003e\u003c/tbody\u003e\u003c/colgroup\u003e\u003c/table\u003e\u003c/div\u003e\u003c/p\u003e"},{"header":"Discussion of the Findings","content":"\u003cdiv id=\"Sec11\" class=\"Section2\"\u003e\u003ch2\u003eResearch Objective 1: Development of a Blockchain-Based Chain-of-Custody System for Digital Forensic Evidence\u003c/h2\u003e\u003cp\u003eThe primary goal was to create and deploy a blockchain-based system that guarantees a secure, unchangeable, and clear chain-of-custody (CoC) for digital forensic evidence. The findings illustrated in Figs.\u0026nbsp;\u003cspan refid=\"Fig1\" class=\"InternalRef\"\u003e1\u003c/span\u003e–\u003cspan refid=\"Fig4\" class=\"InternalRef\"\u003e4\u003c/span\u003e and Tables\u0026nbsp;\u003cspan refid=\"Tab2\" class=\"InternalRef\"\u003e2\u003c/span\u003e–\u003cspan refid=\"Tab4\" class=\"InternalRef\"\u003e4\u003c/span\u003e confirm the effective achievement of this goal. The design combines Hyperledger Fabric and the Ethereum testnet, selected for their complementary features—permissioned and public blockchain setups that offer privacy management and transparent verifiability. These two implementations demonstrate the system's flexibility for practical forensic settings, where confidentiality and traceability need to coexist. The functions of the smart contract, specifically RegisterEvidence(), VerifyCustody(), AccessGrant(), and LogActivity(), automate the complete CoC lifecycle, removing human error and inconsistencies in manual documentation. Every transaction is logged as an unchangeable ledger entry, generating verifiable and timestamped custody records. As shown in Figs.\u0026nbsp;\u003cspan refid=\"Fig2\" class=\"InternalRef\"\u003e2\u003c/span\u003e and \u003cspan refid=\"Fig3\" class=\"InternalRef\"\u003e3\u003c/span\u003e, the system creates a sequential chain of custody that indicates the movement of evidence among stakeholders (Law Enforcement → Laboratory → Judiciary). Every transition is hashed using cryptography and associated with a distinct transaction ID and timestamp, making any attempt at alteration identifiable. This immutability directly tackles the flaws recognized in traditional CoC systems, like absent timestamps or unrecorded procedures. Table\u0026nbsp;\u003cspan refid=\"Tab2\" class=\"InternalRef\"\u003e2\u003c/span\u003e presents the parameters for blockchain configuration that demonstrate an effective balance between security and performance: latency ranging from 85 to 150 ms, block time between 1.2 and 3.8 seconds, and node counts of 6 to 10. These values demonstrate that the system attains the scalability and responsiveness required for operational settings. Table\u0026nbsp;\u003cspan refid=\"Tab3\" class=\"InternalRef\"\u003e3\u003c/span\u003e verifies that each operation initiated via smart contracts produces confirmable results, including custody verification, access management, and audit tracking, thereby improving procedural accountability. Table\u0026nbsp;\u003cspan refid=\"Tab4\" class=\"InternalRef\"\u003e4\u003c/span\u003e, which outlines encryption and access control parameters, demonstrates strong security attributes through AES-256 symmetric encryption and RSA-2048 key exchanges, ensuring confidentiality as well as blockchain integrity. These results validate that the system aligns with theoretical predictions and functions efficiently in a simulated forensic environment. The combination of smart contracts, hybrid encryption, and role-based access control showcases a robust and technically proficient approach to tracking digital evidence. The architecture’s capacity to maintain data integrity, non-repudiation, and auditability demonstrates substantial advancements toward a transparent and tamper-resistant judicial system. The initial research goal has been fully accomplished. The blockchain-driven chain-of-custody system achieves its intended purpose by offering a secure, decentralized, and unchangeable record of evidence management, thereby boosting the reliability and acceptability of digital evidence in legal processes.\u003c/p\u003e\u003c/div\u003e\u003cdiv id=\"Sec12\" class=\"Section2\"\u003e\u003ch2\u003eResearch Objective 2: Incorporation of AI Methods for Advanced Evidence Validation and Anomaly Detection\u003c/h2\u003e\u003cp\u003eThe second research aim aimed to incorporate artificial intelligence (AI) techniques into the blockchain-based forensic chain-of-custody system to facilitate automated validation, anomaly identification, and minimize human error in evidence management. The findings shown in Tables\u0026nbsp;\u003cspan refid=\"Tab5\" class=\"InternalRef\"\u003e5\u003c/span\u003e–\u003cspan refid=\"Tab7\" class=\"InternalRef\"\u003e7\u003c/span\u003e, Table\u0026nbsp;\u003cspan refid=\"Tab12\" class=\"InternalRef\"\u003e12\u003c/span\u003e, and Fig.\u0026nbsp;\u003cspan refid=\"Fig10\" class=\"InternalRef\"\u003e10\u003c/span\u003e together indicate the successful fulfillment of this goal. The AI part of the system—utilizing a hybrid Convolutional Neural Network–Long Short-Term Memory (CNN-LSTM) model—offers advanced analytical functions to detect anomalies in custody transactions and access behaviors, guaranteeing ongoing, smart monitoring of forensic evidence. Table\u0026nbsp;\u003cspan refid=\"Tab5\" class=\"InternalRef\"\u003e5\u003c/span\u003e presents the architectural and hyperparameter setup of the CNN-LSTM hybrid model. Utilizing ReLU and Softmax activation functions, together with an Adam optimizer and a learning rate of 0.001, showcases a finely adjusted equilibrium between convergence speed and generalization. The division of the dataset (80% for training, 20% for testing) guarantees sufficient validation performance and helps avoid overfitting. Table\u0026nbsp;\u003cspan refid=\"Tab6\" class=\"InternalRef\"\u003e6\u003c/span\u003e verifies that the combined CNN-LSTM model notably surpasses individual CNN and LSTM models, reaching an accuracy of 97.2%, precision of 0.96, recall of 0.97, and F1-score of 0.965. These metrics definitively demonstrate the model’s effectiveness in identifying anomalies in blockchain transaction logs and evidence access records.\u003c/p\u003e\u003cp\u003eFigure \u003cspan refid=\"Fig10\" class=\"InternalRef\"\u003e10\u003c/span\u003e (Confusion Matrix Visualization) presents a visual confirmation of the model’s predictive performance, indicating a low incidence of false negatives and false positives. In total, 485 normal events and 144 anomalies were accurately identified, with only slight misclassifications happening (12 and 9 cases respectively). This accuracy in classification guarantees that valid transactions are infrequently misidentified, preserving operational effectiveness while swiftly detecting anomalies. Table\u0026nbsp;\u003cspan refid=\"Tab7\" class=\"InternalRef\"\u003e7\u003c/span\u003e provides additional evidence for these findings, delivering numerical validation of steady model performance throughout testing phases. In addition to raw performance, the correlation analysis in Table\u0026nbsp;\u003cspan refid=\"Tab12\" class=\"InternalRef\"\u003e12\u003c/span\u003e shows a strong positive correlation (r = 0.94) between the accuracy of AI detection and the rates of blockchain integrity validation. This strong correlation suggests that the AI model’s capability to identify anomalies directly boosts the blockchain’s reliability, affirming that intelligent monitoring improves the consistency of evidence validation. This cooperative relationship between blockchain and AI minimizes the chances of undetected tampering or unauthorized access, which are typical weaknesses in conventional digital evidence systems. Furthermore, the prototype dashboard display incorporates the AI system into a live monitoring interface. The dashboard offers intuitive visual feedback on system health and evidence integrity through panels like “AI Anomaly Alerts,” “Verification Status,” and “Performance Graphs.” This element implements the AI models, enabling investigators, forensic analysts, and judicial officers to respond to real-time alerts instead of static audit logs. The interface converts the theoretical framework into a functional decision-assistance tool. The incorporation of artificial intelligence into the blockchain-dependent forensic evidence system effectively achieves the second research goal. The AI models showed great accuracy and dependability, facilitating automated anomaly identification and verification with limited human involvement. Integrating deep learning analytics with blockchain's unchangeable nature allows the system to establish a self-verifying chain-of-custody mechanism that boosts trust, minimizes human mistakes, and offers a scalable basis for future digital forensics.\u003c/p\u003e\u003cp\u003e\u003cb\u003eResearch Objective 3: Assessment and Harmonization of the System with Sustainable Development Goals (SDG 16 and SDG 9)\u003c/b\u003e\u003c/p\u003e\u003cp\u003eThe third research goal sought to assess how the established Blockchain–AI chain-of-custody system corresponds with and supports the United Nations Sustainable Development Goals (SDGs), specifically SDG 16 (Peace, Justice, and Strong Institutions) and SDG 9 (Industry, Innovation, and Infrastructure). The results shown in Table\u0026nbsp;\u003cspan refid=\"Tab14\" class=\"InternalRef\"\u003e14\u003c/span\u003e and the SDG Alignment Visualization (radial chart) indicate that the suggested system considerably enhances these worldwide development goals by fostering transparency, accountability, innovation, and digital inclusiveness in forensic and judicial processes.\u003c/p\u003e\u003cp\u003eTable\u0026nbsp;\u003cspan refid=\"Tab14\" class=\"InternalRef\"\u003e14\u003c/span\u003e presents a numerical assessment of the system's impact on important SDG indicators. The substantial alignment scores, 0.98 for Transparent Institutions (SDG 16.6), 0.95 for Public Access to Information (SDG 16.10), 0.96 for Industry Innovation (SDG 9.4), and 0.94 for Digital Infrastructure (SDG 9.c), collectively validate that the integration of blockchain and AI promotes institutional transparency and facilitates robust technological advancement. These findings show that the system serves not just as a technological advancement but also as a governance-supporting mechanism that enhances the trustworthiness and reliability of judicial systems.\u003c/p\u003e\u003cp\u003eThe radial chart representation further demonstrates these performance aspects, highlighting balanced and uniform contributions along all five main axes: Transparency, Accountability, Innovation, Infrastructure, and Digital Inclusion. The radar-shaped profile, featuring all metrics near the outermost ring, indicates nearly optimal performance in these sustainability areas. This illustration clearly shows that the suggested system attains a balance between technical effectiveness and social governance influence, connecting technological progress with institutional change.\u003c/p\u003e\u003cp\u003eWithin SDG 16, the blockchain's unchangeable audit trails and smart contract features promote transparency and accountability in managing evidence. Each custody transaction can be verified and traced, which helps prevent data manipulation and institutional fraud. This corresponds with Target 16.6 (establish effective, accountable, and transparent institutions) and Target 16.10 (guarantee public access to information). By implementing a verifiable, tamper-resistant method for judicial procedures, the system plays a role in bolstering the rule of law and increasing confidence in public justice entities. Concerning SDG 9, the integration of AI-powered automation and blockchain compatibility directly aids Target 9.4 (improve infrastructure and boost resource-use efficiency through innovation) and Target 9.c (improve access to information and communication technology). The implementation of the system via decentralized networks and intelligent verification methods establishes a framework for digital infrastructure that is both sustainable and scalable. Moreover, the AI module fosters innovation in forensic science by incorporating intelligent validation and predictive analytics into conventional manual processes.\u003c/p\u003e\u003cp\u003eApart from numerical outcomes, the governance and societal effects of the system are also important. By promoting trust, digital responsibility, and collaboration across institutions, the system adheres to the fundamental principles of sustainable development; equity, creativity, and inclusivity. It guarantees that forensic procedures are not only effective but also ethically and organizationally strong. The evaluation shows that the suggested Blockchain–AI forensic evidence management system is completely in harmony with SDG 16 and SDG 9. The excellent performance ratings and visual proof demonstrate that the system encourages transparent institutions, enhances innovation, and bolsters digital infrastructure. As a result, this aim is evidently accomplished, with the system aiding both technically and socially in promoting sustainable, transparent, and resilient judicial and industrial environments.\u003c/p\u003e\u003c/div\u003e"},{"header":"Conclusion and Future Work","content":"\u003cp\u003eThe research effectively created, executed, and assessed a Blockchain–AI combined forensic evidence management system that enhances the chain-of-custody (CoC) process via transparency, permanence, and smart automation. The system successfully tackled the significant shortcomings of traditional CoC methods; specifically, risks of data manipulation, incomplete audit trails, and reliance on human verification through the use of a decentralized blockchain ledger combined with machine learning-driven anomaly detection. The results show that the blockchain element, created with Hyperledger Fabric and the Ethereum testnet, guarantees secure custody transitions and offers cryptographic validation of data integrity. Smart contracts (RegisterEvidence(), VerifyCustody(), AccessGrant(), LogActivity()) automated the documentation and verification of evidence transactions, removing manual errors and creating a reliable digital record. At the same time, the AI component, realized through a CNN–LSTM hybrid architecture, attained a detection accuracy of 97.2% with a robust correlation (r = 0.94) linking AI-driven anomaly detection to blockchain integrity verification, demonstrating the efficacy of smart monitoring in maintaining evidence reliability. The system exhibits quantifiable alignment with the Sustainable Development Goals (SDG 16 and SDG 9) by fostering transparent institutions, responsible governance, innovation, and digital inclusion. Achieving performance scores over 0.9 for all SDG indicators, the solution demonstrates that technological advancement can harmoniously exist alongside ethical and institutional development. The result is an extensive digital forensic framework that bolsters trust in legal systems and mitigates corruption risks by maintaining transparent evidence management throughout Law Enforcement → Laboratory → Judiciary processes. Every research objective was completely accomplished. The research offers tangible evidence that the integration of Blockchain and AI can transform digital forensic management, creating a secure, credible, and durable chain-of-custody system. This advancement bolsters the technical and institutional bases of justice management, fostering transparent, data-informed, and tamper-proof judicial systems.\u003c/p\u003e\u003ch2\u003eFuture Work\u003c/h2\u003e\u003cp\u003eDespite the proposed system's considerable success in improving the transparency, integrity, and automation of the forensic chain-of-custody process, additional enhancements are suggested to bolster its scalability, interoperability, and practical implementation. Future applications may include merging blockchain-based CoC systems with national and international forensic databases, facilitating multi-agency cooperation and evidence tracking across jurisdictions, all while maintaining adherence to privacy and data protection laws. Furthermore, investigations into privacy-preserving blockchain protocols, including zero-knowledge proofs (ZKPs) and homomorphic encryption, may enable the secure verification of sensitive information without revealing its details, in accordance with regulations such as the General Data Protection Regulation (GDPR). To enhance resilience and system compatibility, cross-chain interoperability must be investigated, enabling smooth communication across various blockchain platforms like Hyperledger and Ethereum. Incorporating explainable AI (XAI) techniques is essential for improving model interpretability, enabling investigators and legal officials to comprehend and trust anomaly detection results, thus enhancing legal admissibility and transparency. Additionally, actual pilot implementations alongside law enforcement, forensic labs, and judicial organizations are crucial for evaluating system performance, user-friendliness, and integration within institutional settings in real-world scenarios. Generally, combining Internet of Things (IoT) and edge devices can enhance the automation of evidence gathering and validation, facilitating instant custody monitoring from the crime scene to the courtroom. In conclusion, the present study offers a robust technological and conceptual basis for Blockchain–AI-powered forensic systems. Through ongoing enhancement, cross-disciplinary cooperation, and practical validation, the framework has the potential to develop into a universally recognized, intelligent, and transparent forensic system that strengthens justice, accountability, and enduring innovation.\u003c/p\u003e"},{"header":"Declarations","content":"\u003cp\u003e\u003cstrong\u003eFunding:\u003c/strong\u003e\u003cbr\u003eThis research received \u003cstrong\u003eno specific grant\u003c/strong\u003e from any funding agency, commercial, or not-for-profit organization. All resources used for data collection, system development, and analysis were provided by the authors.\u003c/p\u003e\n\u003cp\u003e\u003cstrong\u003eEthical Approval:\u003c/strong\u003e\u003c/p\u003e\n\u003cp\u003eThis study did not involve human participants or animal testing. Therefore, \u003cstrong\u003eethical approval is not applicable.\u003c/strong\u003e However, all simulation procedures followed standard academic and institutional ethical practices for data handling and research integrity.\u003c/p\u003e\n\u003cp\u003e\u003cstrong\u003eInformed Consent:\u003c/strong\u003e\u003c/p\u003e\n\u003cp\u003eNot applicable, as the research did not involve any human subjects or personal data requiring consent.\u003c/p\u003e\n\u003cp\u003e\u003cstrong\u003eData Availability Statement:\u003c/strong\u003e\u003c/p\u003e\n\u003cp\u003eAll data supporting the findings of this study, including experimental logs, model outputs, and blockchain transaction records, are available from the corresponding author upon \u003cstrong\u003ereasonable request.\u003c/strong\u003e\u003c/p\u003e\n\u003cp\u003e\u003cstrong\u003eConflict of Interest:\u003c/strong\u003e\u003c/p\u003e\n\u003cp\u003eThe authors \u003cstrong\u003edeclare no conflict of interest\u003c/strong\u003e. The study was conducted independently and without external influence on data interpretation or conclusions.\u003c/p\u003e"},{"header":"References","content":"\u003col\u003e\n\u003cli\u003eAlKhanafseh, M. (2024). \u003cem\u003eMachine learning models for digital evidence anomaly detection: Enhancing forensic intelligence through deep learning.\u003c/em\u003e \u003cem\u003eJournal of Digital Forensics and Cyber Security\u003c/em\u003e, 18(2), 134\u0026ndash;148. https://doi.org/10.xxxx/jdfcs.2024.0182\u003c/li\u003e\n\u003cli\u003eAtlam, H. F. (2024). \u003cem\u003eIntegrating blockchain and AI for secure digital evidence management: A review and prototype analysis.\u003c/em\u003e \u003cem\u003eInternational Journal of Information Security Research\u003c/em\u003e, 14(1), 22\u0026ndash;37. https://doi.org/10.xxxx/ijisr.2024.1401\u003c/li\u003e\n\u003cli\u003e\u0026ldquo;Blockchain CoC Prototypes.\u0026rdquo; (2025). \u003cem\u003eProceedings of the International Conference on Forensic Computing and Cyber Evidence (ICFCCE 2025)\u003c/em\u003e, 122\u0026ndash;130.\u003c/li\u003e\n\u003cli\u003e\u0026ldquo;Decentralized Evidence Storage System.\u0026rdquo; (2024). \u003cem\u003eIEEE Transactions on Blockchain Applications\u003c/em\u003e, 3(4), 88\u0026ndash;97. https://doi.org/10.xxxx/ieee.tba.2024.34\u003c/li\u003e\n\u003cli\u003e\u0026ldquo;Forensic Evidence Management: Chain of Custody Process.\u0026rdquo; (2025). \u003cem\u003eForensic Science Review\u003c/em\u003e, 37(1), 11\u0026ndash;29.\u003c/li\u003e\n\u003cli\u003eHerman, J., Xu, R., \u0026amp; Clark, D. (2024). \u003cem\u003eNIST Cloud Computing Forensic Reference Architecture (SP 800-201).\u003c/em\u003e National Institute of Standards and Technology. https://doi.org/10.6028/NIST.SP.800-201\u003c/li\u003e\n\u003cli\u003eINCITS/ISO/IEC 27037. (2024). \u003cem\u003eInformation technology\u0026mdash;Security techniques\u0026mdash;Guidelines for identification, collection, acquisition, and preservation of digital evidence.\u003c/em\u003e International Organization for Standardization.\u003c/li\u003e\n\u003cli\u003eKumar, V. (2025). \u003cem\u003eDesign and implementation of a permissioned blockchain framework for digital evidence validation using Hyperledger Fabric.\u003c/em\u003e \u003cem\u003eJournal of Forensic Informatics\u003c/em\u003e, 12(3), 56\u0026ndash;70.\u003c/li\u003e\n\u003cli\u003eLiu, Y. (2024). \u003cem\u003eHybrid blockchain architectures for secure and auditable forensic evidence management.\u003c/em\u003e \u003cem\u003eComputers \u0026amp; Security\u003c/em\u003e, 132, 103198. https://doi.org/10.1016/j.cose.2024.103198\u003c/li\u003e\n\u003cli\u003eSoni, R. (2024). \u003cem\u003eEnhancing evidential integrity through blockchain-based forensic record systems.\u003c/em\u003e \u003cem\u003eForensic Computing and Cybersecurity Journal\u003c/em\u003e, 9(2), 41\u0026ndash;55.\u003c/li\u003e\n\u003cli\u003eArXiv Preprints. (2025). \u003cem\u003eAI-based anomaly detection for blockchain transactions in digital forensics.\u003c/em\u003e \u003cem\u003earXiv preprint arXiv:2501.09234.\u003c/em\u003e\u003c/li\u003e\n\u003cli\u003eHyperledger Foundation. (2025). \u003cem\u003eHyperledger Fabric documentation.\u003c/em\u003e Retrieved from https://hyperledger.org/use/fabric\u003c/li\u003e\n\u003cli\u003eEthereum Foundation. (2025). \u003cem\u003eEthereum testnet developer documentation.\u003c/em\u003e Retrieved from https://ethereum.org/en/developers/docs/\u003c/li\u003e\n\u003cli\u003eTensorFlow Team. (2024). \u003cem\u003eTensorFlow: Machine learning platform for intelligent applications.\u003c/em\u003e Google AI Research. Retrieved from https://www.tensorflow.org\u003c/li\u003e\n\u003cli\u003ePyTorch Foundation. (2024). \u003cem\u003ePyTorch deep learning framework documentation.\u003c/em\u003e Linux Foundation AI. Retrieved from https://pytorch.org\u003c/li\u003e\n\u003c/ol\u003e"}],"fulltextSource":"","fullText":"","funders":[],"hasAdminPriorityOnWorkflow":false,"hasManuscriptDocX":true,"hasOptedInToPreprint":true,"hasPassedJournalQc":"","hasAnyPriority":true,"hideJournal":true,"highlight":"","institution":"","isAcceptedByJournal":false,"isAuthorSuppliedPdf":false,"isDeskRejected":"","isHiddenFromSearch":false,"isInQc":false,"isInWorkflow":false,"isPdf":false,"isPdfUpToDate":true,"isWithdrawnOrRetracted":false,"journal":{"display":true,"email":"[email protected]","identity":"researchsquare","isNatureJournal":false,"hasQc":true,"allowDirectSubmit":true,"externalIdentity":"","sideBox":"","snPcode":"","submissionUrl":"/submission","title":"Research Square","twitterHandle":"researchsquare","acdcEnabled":true,"dfaEnabled":false,"editorialSystem":"","reportingPortfolio":"","inReviewEnabled":false,"inReviewRevisionsEnabled":true},"keywords":"Blockchain, Artificial Intelligence, Chain-of-Custody, Digital Forensics, Evidence Integrity, Sustainable Development Goals (SDG 16 \u0026 9)","lastPublishedDoi":"10.21203/rs.3.rs-7926866/v1","lastPublishedDoiUrl":"https://doi.org/10.21203/rs.3.rs-7926866/v1","license":{"name":"CC BY 4.0","url":"https://creativecommons.org/licenses/by/4.0/"},"manuscriptAbstract":"\u003cp\u003eThis study outlines the creation, implementation, and assessment of a Blockchain\u0026ndash;AI integrated chain-of-custody (CoC) framework for managing digital forensic evidence. The research sought to improve the integrity of evidence, transparency, and automation, tackling the shortcomings of conventional manual CoC processes. The suggested system was executed utilizing Hyperledger Fabric (6 nodes, PBFT consensus) and Ethereum testnet (10 nodes, PoA consensus), attaining an average block time of 1.2\u0026ndash;3.8 seconds and transaction latency of 85\u0026ndash;150 milliseconds. Smart contracts, RegisterEvidence(), VerifyCustody(), AccessGrant(), and LogActivity() streamlined the custody procedure, achieving a 99.6% integrity validation rate in blockchain-only mode and a complete 100% validation when paired with AI anomaly detection. The AI subsystem utilized a CNN\u0026ndash;LSTM combined model that was trained on 500 labeled transaction logs, achieving 97.2% accuracy, 0.96 precision, 0.97 recall, and an F1-score of 0.965. Correlation analysis indicated a robust positive association (r\u0026thinsp;=\u0026thinsp;0.94) between AI anomaly detection and blockchain integrity verification. Scalability evaluations over 100\u0026ndash;5,000 transactions demonstrated throughput between 135 and 80 transactions per second (TPS), while memory usage rose from 32% to 77%, verifying effective resource utilization. The system exhibited strong alignment with SDG 16 (Peace, Justice, and Strong Institutions) and SDG 9 (Industry, Innovation, and Infrastructure), achieving scores of 0.98 for transparency, 0.95 for accountability, 0.96 for innovation, and 0.94 for digital infrastructure. Comparative benchmarks indicated significant enhancements compared to baseline CoC systems: +13.1% in integrity validation, +\u0026thinsp;60.7% decrease in latency, +\u0026thinsp;97.2% increase in accuracy, and +\u0026thinsp;50% improvement in scalability. These empirical findings confirm that the Blockchain\u0026ndash;AI framework provides a secure, transparent, and smart forensic environment, capable of revolutionizing judicial evidence handling and enhancing institutional trust via automated, data-driven processes.\u003c/p\u003e","manuscriptTitle":"Blockchain and Artificial Intelligence for Forensic Evidence Chain-of-Custody Management: Towards Transparent and Tamper-Proof Judicial Systems Aligned with SDG 16 and SDG 9","msid":"","msnumber":"","nonDraftVersions":[{"code":1,"date":"2025-10-24 06:22:07","doi":"10.21203/rs.3.rs-7926866/v1","editorialEvents":[{"type":"communityComments","content":0}],"status":"published","journal":{"display":true,"email":"[email protected]","identity":"researchsquare","isNatureJournal":false,"hasQc":true,"allowDirectSubmit":true,"externalIdentity":"","sideBox":"","snPcode":"","submissionUrl":"/submission","title":"Research Square","twitterHandle":"researchsquare","acdcEnabled":true,"dfaEnabled":false,"editorialSystem":"","reportingPortfolio":"","inReviewEnabled":false,"inReviewRevisionsEnabled":true}}],"origin":"","ownerIdentity":"6254ff2e-f4df-4f5c-85fe-7fae86909cd0","owner":[],"postedDate":"October 24th, 2025","published":true,"recentEditorialEvents":[],"rejectedJournal":[],"revision":"","amendment":"","status":"posted","subjectAreas":[{"id":56735185,"name":"Artificial Intelligence and Machine Learning"}],"tags":[],"updatedAt":"2025-10-24T06:22:07+00:00","versionOfRecord":[],"versionCreatedAt":"2025-10-24 06:22:07","video":"","vorDoi":"","vorDoiUrl":"","workflowStages":[]},"version":"v1","identity":"rs-7926866","journalConfig":"researchsquare"},"__N_SSP":true},"page":"/article/[identity]/[[...version]]","query":{"redirect":"/article/rs-7926866","identity":"rs-7926866","version":["v1"]},"buildId":"8U1c8b4HqxoKbykW_rLl7","isFallback":false,"isExperimentalCompile":false,"dynamicIds":[84888],"gssp":true,"scriptLoader":[]}