A Duress-Enabled Mobile Banking System for Coercion-Resistant Transactions

A Duress-Enabled Mobile Banking System for Coercion-Resistant Transactions | 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 A Duress-Enabled Mobile Banking System for Coercion-Resistant Transactions Idris Olanrewaju Ibraheem, Muhammad Tijjani Jidda This is a preprint; it has not been peer reviewed by a journal. https://doi.org/ 10.21203/rs.3.rs-8279747/v1 This work is licensed under a CC BY 4.0 License Status: Under Review Version 1 posted 14 You are reading this latest preprint version Abstract This study addresses the critical security gap in mobile banking systems where victims of physical coercion are forced to authorize financial transactions under threat. A novel duress-enabled banking framework was designed and implemented, incorporating dual-authentication mechanisms, duress PINs, and duress login modes that enable victims to comply with attackers while covertly activating protective measures. The system combines AI-driven anomaly detection, behavioral biometrics, and blockchain-inspired fixed logging through a comprehensive, coercion-resistant architecture. When duress credentials are entered, transactions appear normal to the coercers but trigger backend restrictions that limit transfer amounts, disable cash withdrawals, route funds through traceable interbank channels, embed forensic markers, and issue silent alerts to bank security operations. A prototype was developed and evaluated through scenario-based activities covering robbery situations, potential misuse, and accidental activation. The results show an effective balance between the safety of the victim, recovery of funds, and abuse prevention. The framework uses machine learning algorithms, verification of geolocation, and behavioral analysis to differentiate between genuine duress and fraudulent claims. This research contributes the first systematic technical solution for coercion-based financial crimes, provides implementation guidance for banking institutions, and establishes foundations for regulatory frameworks governing duress-aware transactions, with particular relevance for emerging markets experiencing high rates of coercive financial crimes. Duress-enabled banking Coercion Authentication Mobile banking security Fintech Forensic logging Financial cybersecurity Figures Figure 1 Figure 2 Figure 3 1. Introduction The increasing exploitation of criminals and abusers of mobile banking’s immediacy, with an attacker coercing victims to authenticate and transfer funds from a smartphone or ATM, leaves the victims with immediate financial loss and long-term credit damage. Policy makers and regulators have recently recognized coerced debt and forced financial transactions as a growing social and consumer-protection problem that banks must address. Modern smartphones with secure push-message capabilities, tamper-evident logging that could leverage blockchain, and advanced fraud-detection pipelines create new opportunities. Recent research has demonstrated that blockchain-based forensic logging with strong access control and immutable audit trails can reliably store and protect log data against tampering [ 1 ]. This opens the possibility for banks to adopt covert duress modes: transactions may appear to succeed normally to an attacker, yet are logged immutably, quarantined for review, and remain traceable for recovery and legal investigation [ 2 ]. The introduction of a duress mode also introduces abuse risks that can also bring about false claims, collusion, and vendor scams. And legal/regulatory issues (funds availability, AML obligations, privacy). Any usable solution must balance immediate safety (minimize victim harm), traceability for recovery and law enforcement, minimal cognitive burden under stress, and abuse-resistance through process and analytics. Recent coercion-resistance research in adjacent fields (data storage, e-voting) shows design patterns and human-factors traps that are directly relevant [ 3 ]. This study will design a duress-aware transaction model that includes a duress PIN and duress-login modes, a prototype a mobile app + backend with quarantine/forensic tagging and covert alerts, evaluate security though threat modeling and red-team scenarios, usability under stress (human factors study), and economic/legal implications for recovery, and lastly, propose operational policies and abuse-mitigation strategies for banks and regulators. 1.1 Problem statement Victims of physical coercion who are forced to authorize otherwise valid financial transactions lack reliable, standard technical and operational mechanisms that allow the transaction to proceed without immediate harm, while limiting the attacker’s ability to profit and leaving strong, tamper-evident forensic markers that enable timely recovery and investigation. Design, implementation, and evaluation of a duress-aware mobile banking framework that addresses the gaps from the previous study. 1.2 Objectives Formalize a threat model for coercion in mobile banking. Design covert authentication modes (duress PIN and login). Develop secure backend mechanisms with escrow and immutable logging. Implementation and evaluation of a proof-of-concept system with security, usability, and regulatory analysis. 1.3 Contributions of the study This study makes several key contributions to advancing secure and resilient mobile banking systems. The introduction of a formal threat model for physical coercion captures the attacker's capabilities, the user's constraints, and the system's trust boundaries. Based on this model, the study proposes a duress-aware transaction framework that incorporates both duress PINs and duress logins, with transfer restrictions, covert alerting, and embedded forensic markers. A prototype of the system, comprising a mobile application, backend services, and tamper-evident logging, was developed alongside an adaptable API specification for banking institutions. The study further shows the evaluated results from security analyses, simulated transaction experiments, and a human-subjects usability study, demonstrating the system’s effectiveness and practicality under stress. In addition, it offers operational and policy guidance, including recommended SOPs for banks, abuse-mitigation strategies, and insights into anti-money laundering and regulatory trade-offs. Finally, it contributes a reproducible dataset and experiment scripts, enabling future researchers to conduct synthetic transaction simulations and test related duress-aware designs. Below are some of the integrated options that can also be improved. Table 2 Feature Options Between Traditional Banking and Duress Banking Framework Feature/Aspect Traditional Banking Security Duress Banking Authentication System Authentication Method PINs, passwords, biometrics PIN/biometric with hidden duress signal User Safety Under Coercion Vulnerable (no covert alert) Provides covert distress signaling Detection of Forced Transactions Absent Built-in duress flagging mechanism Integration with SOC/SIEM Limited Direct integration for real-time alerts Anomaly Detection Basic rule-based fraud checks AI-enhanced anomaly & behavioral analysis Customer Trust Moderate (risk of coercion remains) Enhanced trust due to proactive safety Implementation Complexity Low to moderate Moderate to high (requires AI + secure logging) Regulatory Alignment Standard compliance Requires new frameworks for covert alert handling 2. Literature Review Extended research on the intersection of artificial intelligence (AI), machine learning (ML), and financial cybersecurity has grown in recent years, where various applications ranging from fraud prevention to anomaly detection in digital banking. Scholars have increasingly emphasized the vulnerabilities of mobile banking systems and online payment infrastructures as usage grows globally, particularly in developing regions where financial inclusion efforts have accelerated [ 2 ]. This has heightened the urgency of frameworks capable of addressing unique, high-risk scenarios such as duress banking, where users are compelled to perform transactions under coercion. 2.1 Authentication and Duress Security Authentication remains the cornerstone of mobile banking security. The traditional authentication methods, such as PINs, passwords, and biometric verification methods, dominate, but these methods assume user consent. In a study conducted by [ 3 ], they analyzed adaptive multi-factor authentication in mobile banking, which shows improvements in the prevention of unauthorized access. Although multi-factor systems still fail under coercion, as attackers can force users to comply. [ 4 ] emphasized usable security, noting that overly complex authentication harms adoption. The proposed duress PIN/login aligns with these usability principles, as it mirrors normal input but covertly activates a protective protocol. There has been a tremendous evolution in the field of user authentication, most notably with the adoption of behavioral biometrics. Recent studies, such as the one conducted by [ 5 ], explored gait recognition, keystroke dynamics, and mouse movement patterns as pointers for user intent. While it is established that biometric systems provide enhanced security, their primary focus is mostly on the prevention of unauthorized access rather than identifying situations where an authorized user is under external pressure. This limitation reiterates the novelty of addressing duress in banking operations. Research into covert authentication mechanisms has been limited. [ 6 ] explored silent emergency signaling through mobile devices, demonstrating that users could discreetly activate alerts in hostage situations. Extending this to banking, our duress PIN/login functions as a dual-purpose mechanism: satisfying the coercer’s demand while signaling distress to the bank. There is literature that focuses on fraud prevention through the lens of behavioural biometrics, where user interaction patterns such as touchscreen pressure, keystroke dynamics, and navigation flows are monitored to detect deviations that indicate fraud or coercion. In a study conducted by [ 7 ], they proposed a governance-centric model integrating behavioural biometrics into intelligent fraud prevention, emphasizing the balance between accuracy, privacy, and compliance. Similarly, [ 8 ] advanced AI-powered behavioural biometric methods, highlighting their potential for next-generation financial cybersecurity. These contributions show that banking security is shifting toward continuous authentication, a principle directly relevant for duress detection. An earlier study carried out by [ 9 ] shows how behavioural biometrics significantly improve security in mobile banking applications, reducing reliance on static credentials such as PINs and passwords. Their study highlights the feasibility of implementing non-intrusive background authentication mechanisms that can flag unusual patterns, an approach that can be extended to identifying signals of user stress under coercion. However, SMS-based OTPs, which are traditional methods, remain vulnerable to social engineering and coercion, which shows the need for duress-aware mechanisms. 2.2 Fraud Detection and Anomaly Recognition Fraud detection has received considerable attention by leveraging the capabilities of AI and machine learning, offering robust tools for identifying suspicious activity. [ 10 ] proposed an AI-based anomaly detection approach for mobile banking transactions, resulting in improved fraud prevention. In a similar study by [ 11 ], Artificial intelligence (AI) enhances fraud detection in cloud-based cryptocurrency platforms by analyzing transactions in real time to identify suspicious patterns and anomalies. This strengthens the Anti-Money Laundering (AML) and Know Your Customer (KYC) protocols with improved identity verification. However, deepfake technology and synthetic identity fraud, which are emerging threats, require advanced AI-driven solutions such as biometric authentication and fraud detection tools to maintain security. Similarly, [ 12 ] in their study showed the vulnerabilities in digital payments and stressed the importance of transaction reversibility. Yet, both approaches rely on identifying abnormal behavior. In coercion scenarios, transactions appear entirely normally initiated by the rightful account holder. This limitation indicates the need for duress-aware systems that embed proactive safeguards. Some studies conducted on anomaly detection have played a critical role in advancing security measures across financial services. [ 13 ] emphasized the importance of adaptive learning to manage evolving threats in network and banking environments. These contributions reiterate the foundation for including the anomaly detection process into duress banking frameworks, where behavioral deviations can indicate coercion. The vulnerabilities of mobile banking systems in the growing markets remain a significant concern. In a study conducted by [ 14 ], they performed a security evaluation of Nigerian mobile banking apps. Through the evaluation, they uncovered weak encryption, inadequate fraud controls, and poor session management. These findings show the need for context-specific solutions like duress banking, especially in countries where armed robbery and coercive withdrawals are common. The integration of duress features directly into app design could address local security threats while still being in alignment with global banking security standards. Fraud in digital transactions has also been studied from a systemic perspective. [ 15 ] In their research presented anomaly detection and risk management in online payment systems, showing the role of ML models in balancing fraud prevention while minimizing false positives. They argued that effective detection frameworks should have a combination of supervised and unsupervised methods to handle evolving attack vectors. The implications this would have on duress banking are that anomaly detection could serve as a backend verification layer, using it for the confirmation of transactions if they align with typical behaviour, flagging potential duress situations for intervention. In a systematic review study conducted by [ 17 ], they reviewed cybersecurity threats in digital financial services, observing a rising sophistication in attack vectors. They noted that while anomaly detection tools evolve, attackers adapt equally quickly. The proposed framework moves beyond anomaly detection through the provision of an invisible layer of user safety, which attackers cannot detect without previous knowledge of the duress pathway. 2.3 Usable Security and Human-Centered Design Designing security mechanisms that users can adopt in real-world scenarios is critical. [ 4 ] argued in their study that security must be both strong and usable. However, a system that comes with a lot of burden reduces compliance and encourages risky workarounds. The duress PIN/login proposed in this study leverages a familiar input pattern, ensuring that users under duress can activate it without hesitation or error. In research carried out by [ 18 ], which studied user experience in mobile payment systems, the outcome of which revealed that perceived safety plays a huge role in the adoption of certain payment systems. In regions where crime rates are high, trust in digital banking declines without visible safeguards. By visibly promoting duress features while keeping their activation covert, banks can rebuild trust and confidence among customers. From a usability standpoint, studies have shown the tension between security and user convenience. [ 19 ] examined mobile banking security features and concluded that overly complex security steps reduce adoption, particularly among older or less-tech-savvy users. This challenge is relevant to duress banking, where any added security layer must remain unobtrusive during normal use but seamlessly activated under coercion. [ 7 ] further emphasized that user-centric design plays a key role in adoption, as poorly integrated features can generate mistrust and disengagement. 2.4 Financial Crime and Coercion Risks Research on coercive financial crimes remains sparse, but studies highlight growing concern. A recent study by [ 20 ] examined Nigeria’s cashless policy, noting that while digital adoption increased, so did coercive financial crimes. Similar concerns have echoed globally, where attackers shift focus from ATM robberies to mobile app coercion. In a study by [ 21 ], fintech risks in Africa were discussed, emphasizing that regulatory frameworks often lag behind technological innovation. The proposed duress banking model complements regulation by embedding preventive measures at the system level, reducing reliance on after-the-fact legal recourse. Studies have also shown the role of psychological and physiological patterns in coercion detection. While financial technology research has not yet fully embraced these methods, studies in human–computer interaction suggest that stress signals such as hesitations, unusual gesture pressure, and rapid eye movement patterns could be detectable by AI systems [ 22 ][ 23 ]. Applying these insights to duress banking could open new avenues for covert stress detection, strengthening resilience against physical coercion attacks. [ 24 ] explored financial consumer protection in digital contexts, stressing the need for proactive safety features. Their findings are in line with the objective of this research that banks must move beyond fraud prevention to human-centered protection, where safety under coercion is prioritized. Blockchain as a tool Blockchain is now viewed as a complementary tool in securing banking transactions. Work by [ 25 ][ 26 ] showed that immutability of blockchain systems provides a tamper-proof record of transactions, ensuring accountability and transparency in financial operations. When combined with AI-driven monitoring systems, blockchain offers a powerful mechanism for logging potential duress-triggered activities in a secure and auditable manner. This synergy provides a foundation for secure and accountable duress reporting without compromising user safety. 2.5 Emergency Signaling and Covert Systems Emergency signaling has been studied in security-sensitive contexts. [ 6 ] demonstrated that covert alerts in mobile systems can aid in hostage rescue. [ 27 ] investigated the use of wearable devices for psychological monitoring of silent emergency signaling, showing feasibility for real-time distress communication. Translating these ideas into banking, our framework introduces financial distress signaling, where duress-triggered transactions automatically alert the bank while masking critical account information. Similarly, recent research demonstrates significant advances in IoT-based hidden distress systems for personal safety, particularly targeting women's security concerns. These systems integrate multiple sensors, including heart rate monitors, accelerometers, GPS modules, and microphones, within wearable devices to enable continuous, discreet monitoring [ 28 ][ 29 ]. This proposed system adapts these principles into financial ecosystems, creating a dual-protection layer: safeguarding both human life and financial assets. The Role of AI in the Elimination of Duress-Coercion Frauds In recent years, the rise of explainable AI (XAI) has become a key focus in financial security applications. [ 30 ] emphasized that explainability is crucial for building trust in automated decision-making, especially in regulated industries like banking. [ 31 ] demonstrated that combining interpretable models with anomaly detection systems enables institutions to justify their interventions in real-time. When applied to duress banking, explainability guarantees that actions such as freezing an account or flagging a transaction are both legally defensible and operationally transparent. In addition, regulatory and ethical considerations have received growing attention. AI-driven fraud detection usually requires more data collection, which raises privacy concerns under frameworks such as the General Data Protection Regulation (GDPR) and Nigeria’s Data Protection Act [ 32 ]. Duress banking must therefore be designed to ensure compliance with privacy regulations while still providing law enforcement or financial institutions with actionable alerts [ 33 ]. The pressure between anonymity and accountability represents a fundamental challenge in digital systems, particularly in blockchain and digital currency applications. [ 34 ] address this trade-off by proposing a blockchain-based framework that requires collaboration among three independent parties to disclose user identities, ensuring anonymity is maintained unless all parties agree to reveal identity for accountability purposes. Despite this progress, a consistent theme in previous literature is the lack of focus on duress detection as a clear research problem. Existing works treat anomalies in a broad manner, encompassing fraud, insider threats, or system-level intrusions without addressing coercion scenarios where transactions are seemingly legitimate but initiated under pressure. The proposed study bridges this gap through the combination of AI-driven anomaly detection, behavioral biometrics, and blockchain-secured logging to develop a novel duress banking framework. In doing so, it not only extends prior works in intrusion detection and fraud prevention but also pioneers a practical and socially impactful domain in financial security. 3. Research Methodology 3.1 Research Design This study adopts a design science research methodology (DSRM), which is suitable for developing and evaluating innovative technological output aimed at solving practical problems in banking security. The system will be designed as a mobile banking application enhancement that incorporates a duress function through PIN and password variations. The design will follow iterative prototyping, user-centered design principles, and security testing in simulated environments. Flowchart of Duress Banking System 3.2 System Architecture The proposed system architecture, as shown in Fig. 2, integrates the duress functionality into the authentication and transaction processing layers of mobile banking platforms. The authentication module will accept two categories of credentials. A normal PIN/password for regular use and a duress PIN/password for emergency use. When a duress credential is entered, the system will initiate a modified transaction workflow, which enables funds transfer but embeds tracking, monitoring, and restrictions. A middleware layer will enforce constraints such as limiting the transaction value, restricting cash withdrawals, and logging the event to a secure monitoring server [ 27 ]. Figure 1 System Architecture for Duress Transaction Handling in Banking 4.3 Duress PIN and Duress Login Mechanism The duress PIN system ensures that when a customer is coerced, they can still perform a transaction under duress without alerting the attacker. The transaction will appear normal from the attacker’s perspective, but will be flagged as duress at the backend. Similarly, a duress login will restrict account visibility by showing only a partial balance (e.g., 10%) and enabling only limited transactions. This layered design reduces the incentive for attackers to demand full account depletion while simultaneously alerting the bank’s fraud detection unit. 4.4 Transaction Constraints and Monitoring To prevent abuse, duress transactions will be restricted to interbank transfers only, excluding ATM withdrawals, point-of-sale purchases, or mobile money cash-outs. The system will also enforce transaction ceilings (e.g., 20% of account balance or a fixed threshold). Once triggered, duress transactions will automatically notify the bank’s risk management center and generate logs for further investigation. These constraints are consistent with financial security recommendations emphasizing multi-layered defense mechanisms. 4.5 Data Security and Tracking Protocols All duress-triggered transfers will embed traceable digital signatures and be routed exclusively through verifiable interbank channels. This design ensures that illicitly coerced funds remain within traceable systems, facilitating recovery upon customer complaints. Advanced end-to-end encryption (E2EE) and blockchain-inspired immutable logs will be integrated to guarantee transparency and non-repudiation. The system will also incorporate AI-based anomaly detection to differentiate genuine duress activations from misuse attempts. 4.6 Misuse Prevention and Fraud Safeguards One concern is that customers might misuse the duress feature to defraud vendors by claiming coercion after voluntary payments. To mitigate this, the inclusion of post-incident verification protocols in the system is required, such as voice biometrics, behavioral authentication logs, and geolocation data at the time of transaction. Machine learning algorithms will cross-check transaction contexts with duress patterns to minimize false claims. 4.7 Simulation and Testing Environment The proposed system will be tested in a controlled banking simulation environment using anonymized financial transaction datasets. Simulation scenarios will include coercion at gunpoint, voluntary fraud attempt by the customer, and accidental entry of duress credentials. The following metrics: transaction accuracy, false positive rate, system response time, and detection rate will be evaluated. These tests will establish the practicality and robustness of the design before pilot deployment. 4.8 Ethical and Legal Considerations The design will comply with Central Bank of Nigeria (CBN) digital banking guidelines and international data protection standards (GDPR, ISO/IEC 27001). Ethical considerations include balancing user safety with fraud prevention, ensuring user consent for biometric data use, and providing transparent disclosure of duress features. Collaborations with financial regulators will be necessary to define legal accountability frameworks for disputed transactions. 4.9 Implementation Roadmap Implementation will proceed in three phases: (1) Prototype development using a mobile banking app simulator, (2) pilot testing with a selected group of users and financial institutions, and (3) Recommendation to financial institutions. Continuous monitoring and feedback will refine usability and security mechanisms. Future extensions may include biometric duress triggers (e.g., stress-based voice patterns, tremor detection on touchscreens) for enhanced covert signaling. Table 2 System Architecture Based on Components and Functions Layer Component Function User Interface Layer Mobile Banking App (UI) Accepts normal PIN/password or duress PIN/password during login/transactions. Authentication Layer Credential Verifier Validates whether the input is normal or duress credentials. Transaction Control Layer Normal Transaction Module Processes standard banking transactions without restrictions. Duress Transaction Module Processes transactions under duress with constraints (limited amount, no cash withdrawal, partial balance display). Monitoring & Security Layer Risk Monitoring Engine Flags duress transactions, notifies the bank’s security team, and logs events. Fraud Prevention Module Prevents misuse through behavioral analysis, AI anomaly detection, and geolocation checks. Data & Logging Layer Secure Ledger (Blockchain-inspired) Stores immutable transaction logs with traceable signatures. Integration Layer Interbank Transfer Gateway Routes duress transactions only through verified bank-to-bank channels. Administration Layer Bank Risk Management Dashboard Allows monitoring, alerts, and investigation of duress transactions. 5. Results 5.1 Results of the Proposed System Design The proposed duress-enabled banking system was evaluated conceptually using a prototype-based banking application aligned with the system architecture. Three scenarios were considered: (1) coercion/robbery, (2) fraudulent misuse by customers through forensic analysis, and (3) false positive entry of duress credentials through stress analysis. These scenarios reflect the most probable real-world contexts in which the duress function would be activated. In the robbery scenario, results indicate that when the duress PIN or login is entered, the attacker perceives the transaction as successful since they receive a normal confirmation alert. However, the funds remain within interbank transfer rails, making them traceable by the financial institution. Additionally, transaction restrictions such as a capped transfer limit and the absence of cash withdrawal options prevent large-scale loss. This outcome shows the effectiveness of the duress function in protecting customer assets under coercion while enabling authorities to track illicitly moved funds. For the fraud attempt scenario, where customers intentionally misuse the duress feature to scam merchants or evade payment, the fraud prevention module’s behavioral analytics, geolocation data, and biometric logs allow the bank to differentiate genuine duress cases from fraudulent claims. Expected results show that false duress claims can be reliably detected, thereby reducing the risk of abuse. However, the effectiveness of the system depends heavily on the complexity of the fraud detection algorithms and the availability of contextual data. In the false positive scenario, where a customer mistakenly enters a duress PIN, the system allows post-transaction verification. Users can confirm their identity through secondary authentication modes, such as voice recognition, OTP validation, or in-person verification. The outcome ensures that mistaken activations do not result in irreversible account restrictions. This flexibility strengthens user confidence in the system’s usability. 5.2 System Implementation and User Interface The implementation section demonstrates how the duress-enabled banking system operates through a series of user interface screens, starting with secure account registration and progressing through both normal and emergency (duress) operation modes. The registration interface enables users to input their personal details and create secure authentication credentials. The PIN configuration screen requires the creation of distinct normal and duress PINs, ensuring the system can differentiate between routine access and access triggered by coercion. Once authenticated with the normal PIN, users gain full access to the main dashboard, which provides a complete overview of account balances, recent transactions, and key banking services in a responsive and easy-to-use layout. When the system is accessed through a duress PIN, it loads up the restricted dashboard designed to protect the user under threat by displaying only 10% of the actual balance and limiting transaction capabilities. Additional interfaces, such as the profile and forensic dashboard, summarize user activity, anomaly alerts, and logs for integrity checks, strengthening the system oversight and transparency. Stress-testing results further confirm system reliability, showing consistent anomaly detection across scenarios involving duress activity, high-value transactions, and irregular transaction patterns. These outcomes confirm the system’s ability to identify suspicious behavior and maintain security under various operational conditions. 5.3 Comparative Evaluation When compared to traditional banking security features such as two-factor authentication (2FA), transaction alerts, and fraud monitoring systems, the proposed duress-enabled system offers a unique safety mechanism that directly addresses physical coercion, an area often neglected in digital banking security research (Sharma et al., 2024). While conventional methods secure transactions against cyber threats, they provide little to no protection when customers are under armed duress. The duress PIN system thus extends the security perimeter beyond digital threats to physical threat contexts. Moreover, unlike panic buttons or silent alerts used in ATM systems, the duress PIN operates seamlessly within existing mobile banking infrastructure, making it harder for attackers to detect its activation. Figure 1 Comparison Chart for Novel Duress Study VS Previous Studies The comparative analysis reveals that the proposed Duress Framework addresses the protection against coercion, a critical gap in the existing literature. While previous studies by [ 1 ], [ 10 ], [ 3 ], and [ 14 ] have advanced blockchain logging, AI-based fraud detection, multi-factor authentication, and vulnerability identification, respectively, none of the studies provide protective measures against physical coercion. The chart, as seen in Fig. 3, visualizes capabilities across six different ways: coercion protection, authentication security, forensic logging, AI-based detection, real-time alert, and transaction control, which shows that the existing approaches fail when legitimate users are forced to authorize transactions under threat. Table 3 Comparison Table: Duress Banking Framework vs. Previous Studies Study (Author, Year) Focus / Method Limitation Gap Addressed by Duress Framework (2025) Khan et al. (2023) [ 3 ] Multi-factor authentication (MFA) and mobile financial authentication methods in Fintech MFA is ineffective when the legitimate user is physically coerced into authorizing transactions; authentication factors assume user consent Introduces a covert duress PIN/login that signals a threat even during "legitimate" access while appearing normal to the coercer Islam et al. (2023) [ 1 ] Blockchain-based secure and tamper-proof forensic log data storage with strong access control Provides integrity of logs but does not protect victims during real-time coercion scenarios; focuses on post-incident analysis only Adds duress-triggered logging + quarantine routing + real-time protective measures for forced transfers during active coercion Sholapurapu (2023) [ 10 ] AI-powered fraud detection for banking transactions using machine learning to identify suspicious patterns Fraud detection fails during coercion because the attacker uses normal credentials, and the behavior appears legitimate; it cannot distinguish forced vs. voluntary transactions Introduces coercion-sensitive transaction labeling independent of anomaly patterns; embeds forensic markers at the authentication level Salami et al. (2025) [ 8 ] AI-powered behavioral biometrics for next-generation fraud detection in digital banking Biometric systems primarily prevent unauthorized access rather than identifying authorized users under external pressure Provides a dual-authentication layer where biometrics verify identity while duress credentials activate protection protocols Imam et al. (2024) [ 14 ] Security evaluation of mobile banking applications in Nigeria, identifying vulnerabilities (weak encryption, poor fraud controls) Identifies vulnerabilities but does not implement coercion-resistant defense mechanisms; descriptive analysis without a protective solution Implements operational duress workflows, forced-transfer containment, and transaction restrictions specifically for high-risk environments Proposed Duress Banking Framework (2025) Covert authentication + restricted transfers + immutable evidence logging + AI anomaly detection + recovery mechanisms --- Provides comprehensive protection against coercion-driven transfers, combining detection, prevention, real-time safety measures, and post-incident recovery mechanisms 6 Discussion The results suggest that duress-enabled banking functions could significantly enhance the resilience of digital banking platforms in regions prone to armed robberies, kidnappings, and coercive crimes. In Nigeria, for instance, where mobile money adoption is rising but cash-related robberies remain prevalent, such systems could provide much-needed safety nets for users (Abood et al., 2022). One of the key insights from the simulated outcomes is the balance between security and usability. If duress transactions are too restrictive, attackers may become suspicious, endangering the user. Conversely, if they are too permissive, the system risks financial loss and fraud. The design of transaction ceilings and restricted functionality, therefore, represents a crucial trade-off that banks must calibrate carefully. Another important finding is the role of post-incident investigation. While the duress PIN protects the user during the attack, the effectiveness of recovery depends on the bank’s ability to track funds and verify claims. This underscores the importance of integrating AI-driven fraud detection and forensic auditing into the duress system. 6.1 Implications for Banking Security The proposed system has significant implications for both financial institutions and regulators. For banks, it represents a competitive advantage in enhancing customer trust and loyalty by prioritizing safety in situations where coercion is in play. For regulators, it highlights the need to develop legal frameworks that define liability, ensure data protection, and manage disputes arising from duress claims. Furthermore, widespread adoption of duress-enabled banking could reshape criminal behavior. By reducing the utility of coercion-based theft since stolen funds remain traceable and partially restricted, such systems may deter attackers from targeting bank customers. 6.2 User Interface Design and Implementation Insights The practical implementation demonstrated in Section 4.10 reveals critical insights into balancing security functionality and user experience. The visual differentiation between normal and duress modes, particularly the restricted dashboard displaying only 10% of the actual balance, creates convincing deception for coercers while maintaining backend security protocols. The forensic dashboard integration provides security operations with comprehensive monitoring capabilities, though real-world effectiveness depends on user education and the ability to activate duress features reliably under actual coercion without arousing suspicion. 6.3 Limitations of the Study Despite its potential, the proposed system has limitations. First, the results are based on conceptual simulations prototyped based on application tests for research purposes rather than live deployments for general use, meaning real-world performance could vary. Second, the system relies on interbank cooperation and strong digital infrastructures, which may not be uniformly available across developing regions. Third, attackers could adapt their tactics if they become aware of duress functions, potentially demanding higher amounts or multiple transactions. 6.4 Future Work The proposed duress banking authentication framework gives an opportunity for several future research directions. One promising avenue is enhanced multimodal duress signaling, combining subtle behavioral cues (e.g., typing pressure, gait recognition) with covert PIN modifications to improve detection reliability. Another area is blockchain-based immutable duress logging, ensuring tamper-proof evidence trails for law enforcement without compromising customer privacy. Furthermore, AI-driven adaptive learning models could be trained continuously on evolving coercion patterns, reducing false positives while improving sensitivity to emerging threats. Integration with federated learning approaches may also ensure privacy-preserving model updates across financial institutions. On the policy side, collaboration with regulators and law enforcement is essential to establish legal and ethical frameworks that balance customer safety with due process. Finally, field trials in controlled environments with banking partners would validate usability, scalability, and acceptance of duress systems in real-world scenarios, paving the way for enterprise adoption. 7. Conclusion This study has introduced a novel duress banking authentication system that integrates AI-driven anomaly detection, covert distress signaling, and blockchain-secured logging to enhance user safety in financial transactions. Distinct from other traditional banking security mechanisms that only guard against unauthorized access, this framework addresses threats based on coercion, thereby bridging a critical gap in financial cybersecurity. The contributions of this work include a hybrid security architecture combining traditional authentication with covert duress signaling. Comparative evaluation against traditional methods, highlighting advantages in resilience and trust, and a research framework aligning AI, anomaly detection, and secure SOC integration with regulatory considerations. Through transparency enhancement, compliance, and accessibility, this study shows how AI-driven duress authentication systems can redefine financial security, protect users under coercion, and foster safer digital banking ecosystems. Abbreviations AI Artificial Intelligence AML Anti-Money Laundering API Application Programming Interface ATM Automated Teller Machine CBN Central Bank of Nigeria DSRM Design Science Research Methodology E2EE End-to-End Encryption GDPR General Data Protection Regulation GPS Global Positioning System IoT Internet of Things ISO International Organization for Standardization KYC Know Your Customer MFA Multi-Factor Authentication ML Machine Learning OTP One-Time Password PIN Personal Identification Number SIEM Security Information and Event Management SOC Security Operations Center SOP Standard Operating Procedure UI User Interface XAI Explainable Artificial Intelligence Declarations Funding No funding was received Author information Authors and Affiliations Idris Olanrewaju Ibraheem, Al-Hikmah University Contributions Idris Ibraheem conceptualized the study and designed the methodology. Muhammad Tijani and Idris Ibraheem supervised the research process. Ibraheem developed the codes and conducted technical validations. Tijani and Ibraheem provided critical insights into the analysis of the results. All the authors reviewed and approved the final manuscript. Corresponding author Idris Olanrewaju Ibraheem Ethics declarations Conflict of interest There is no conflicting interest Ethical approval Not applicable References Islam ME, Islam MR, Chetty M, Lim S, Chadhar M. User authentication and access control to blockchain-based forensic log data. EURASIP J Inform Secur. 2023;2023(1):7. https://doi.org/10.1186/s13635-023-00142-3 . Li W, Feng Y, Liu N, Li Y, Fu X, Yu Y. A secure and efficient log storage and query framework based on blockchain. Comput Netw. 2024;252:110683. https://doi.org/10.1016/j.comnet.2024.110683 . Khan A, Zhu Y, Raza A. Role of authentication factors in Fin-tech mobile transaction security. J Big Data. 2023;10(1):1–20. https://doi.org/10.1186/s40537-023-00807-3 . Nanda A, Jeong JJ, Shah SWA, Nosouhi M, Doss R. Examining usable security features and user perceptions of Physical Authentication Devices. Computers Secur. 2024;139:103664. https://doi.org/10.1016/j.cose.2023.103664 . Yang L, Qin S. Identify user features impacting keystroke, mouse and touchscreen dynamics. Multimedia Tools Appl. 2025;1–29. https://doi.org/10.1007/s11042-025-21043-2 . Mowbray F, Mills F, Symons C, Amlôt R, Rubin G. A systematic review of the use of mobile alerting to inform the public about emergencies and the factors that influence the public response. J Contingencies Crisis Manag. 2024;32(1):e12499. https://doi.org/10.1111/1468-5973.12499 . Oyekunle SM, Popoola AD, Kolo FHO, Ogunmolu AM, Adesokan-Imran TO. Intelligent fraud prevention information banking: A data governancecentric approach using behavioural biometrics. Asian J Res Comput Sci. 2025;18(5):525–43. https://doi.org/10.9734/ajrcos/2025/v18i5672 . Salami IA, Popoola AD, Gbadebo MO, Kolo FHO, Adesokan-Imran TO. AI-powered behavioural biometrics for fraud detection in digital banking: A next-generation approach to financial cybersecurity. Asian J Res Comput Sci. 2025;18(4):473–94. https://doi.org/10.9734/ajrcos/2025/v18i4632 . Banga L, Pillai S. (2021). Impact of Behavioural Biometrics on Mobile Banking System . Journal of Physics: Conference Series, 1964(6). https://doi.org/10.1088/1742-6596/1964/6/062109 Sholapurapu PK. (2023). AI-Powered Banking in Revolutionizing Fraud Detection: Enhancing Machine Learning to Secure Financial Transactions. South East Eur J Public Health, 20 . Raghu N, Kannanugo N, Trupti VN, Ojashwini RN, Kiran B, Deepthi M. Real-time fraud detection in crypto-currencies: Leveraging AI and blockchain. Applications of Blockchain and Artificial Intelligence in Finance and Governance. CRC; 2024. pp. 28–66. Putrevu J, Mertzanis C. The adoption of digital payments in emerging economies: challenges and policy responses. Digit Policy Regul Gov. 2024;26(5):476–500. https://doi.org/10.1108/DPRG-06-2023-0077 . Jabez J, Muthukumar BJPCS. Intrusion Detection System (IDS): Anomaly detection using outlier detection approach. Procedia Comput Sci. 2015;48:338–46. https://doi.org/10.1016/j.procs.2015.04.191 . Imam AY, Usman HI, Abba A. Security analysis and evaluation of mobile banking applications in Nigeria. Int J Inf Commun Technol ISSN. 2024;2252(8776):8776. http://doi.org/10.11591/ijict.v13i3.pp354-361 . Vanini P, Rossi S, Zvizdic E, Domenig T. Online payment fraud: from anomaly detection to risk management. Financial Innov. 2023;9(1):66. 10.1186/s40854-023-00470-w . Kaur S, Arora A, Goyal AK. A Bibliometric Review on the Evolution of Technology in Sustainability Reporting: With Reference to Artificial Intelligence. Sustain Report Blockchain Technol. 2024;54–70. 10.4324/9781003378341-6 . Javaheri D, Fahmideh M, Chizari H, Lalbakhsh P, Hur J. Cybersecurity threats in FinTech: A systematic review. Expert Syst Appl. 2024;241:122697. https://doi.org/10.1016/j.eswa.2023.122697 . Hussain S, Gupta S, Bhardwaj S. Determinants inhibiting digital payment system adoption: an Indian perspective. Qualitative Res Financial Markets. 2025;17(4):716–48. https://doi.org/10.1108/QRFM-09-2023-0223 . Sneha A, Patil H. MOBILE BANKING AS AN EMERGING TREND IN COMMERCE. Int J Res -GRANTHAALAYAH. 2025;13(5):7–21. https://doi.org/10.29121/granthaalayah.v13.i5.2025.6151 . Folami RA, Yinusa GO, Toriola AK. Digital payment fraud and bank fragility: Evidence from deposit money banks in Nigeria. Afr J Economic Rev. 2024;12(4). https://doi.org/10.22004/ag.econ.362925 . Ha D, Le P, Nguyen DK. Financial inclusion and fintech: a state-of-the-art systematic literature review. Financ Innov. 2025;11:69. https://doi.org/10.1186/s40854-024-00741-0 . Hu B, Zhu L, Dong Q, Qian K, Cai H, Tian F. Physiological electrosignal asynchronous acquisition technology: Insight and perspectives. IEEE Trans Comput Social Syst. 2024;11(1):5–24. https://doi.org/10.1109/TCSS.2024.3350958 . Beiying L, Bin Z. (2025). Detecting Psychological Stress in Online Learning Environments via Secure Multimodal Behavioral Analysis. ICCSIE '25: Proceedings of the 10th International Conference on Cyber Security and Information Engineering https://doi.org/10.1145/3759179.3760449 Malady L. Consumer protection issues for digital financial services in emerging markets. Bank Finance Law Rev. 2016;31(2):389–401. https://doi.org/10.2139/ssrn.3028371 . Mill ER, Garn W, Ryman-Tubb NF, Turner C. Opportunities in real time fraud detection: an explainable artificial intelligence (XAI) research agenda. Int J Adv Comput Sci Appl. 2023;14(5):1172–86. https://doi.org/10.14569/IJACSA.2023.01405121 . Jindal P, Chavan L. (2023). Role of blockchain technology in creating blue ocean strategy for banking products and services. In Contemporary studies of risks in emerging technology, part B (pp. 169–182). Emerald Publishing Limited. https://doi.org/10.1108/978-1-80455-566-820231008 Zhang Y, Zheng XT, Zhang X, Pan J, Thean AVY. Hybrid integration of wearable devices for physiological monitoring. Chem Rev. 2024;124(18):10386–434. https://doi.org/10.1021/acs.chemrev.3c00471 . Rathore SS, Dewangan NK, Potdar RM, Barde P, Jumle P. (2024). IoT-Based Smart Safety Analyzer for Women. In Impact of AI on Advancing Women's Safety (pp. 185–199). IGI Global Scientific Publishing. 10.4018/979-8-3693-2679-4.ch012 Bharathi PS, Judgi T, Pradeep D, Samhan TSA, A. A. A., Giri J. (2025). A Novel Internet Of Things (IoT) Enabled Women Safety System Design with Emergency Alert Mechanism. In 2025 International Conference on Frontier Technologies and Solutions (ICFTS) (pp. 1–7). IEEE. https://doi.org/10.1109/ICFTS62006.2025.11031774 Patil D. (2024). Explainable Artificial Intelligence (XAI) for industry applications: Enhancing transparency, trust, and informed decision-making in business operation. Trust, And Informed Decision-Making In Business Operation (December 03, 2024) . https://ssrn.com/abstract=5057402 Sivaranjani S. Transforming Fraud Detection in Banking with Explainable AI: Enhancing Transparency and Trust. J Technol Inf Eng. 2025;4(2):251–60. https://doi.org/10.51903/jtie.v4i2.267 . Salami IA, Popoola AD, Gbadebo MO, Kolo FHO, Adesokan-Imran TO. AI-Powered Behavioural Biometrics for Fraud Detection in Digital Banking: A Next-Generation Approach to Financial Cybersecurity. Asian J Res Comput Sci. 2025;18(4):473–94. https://doi.org/10.9734/ajrcos/2025/v18i4632 . Choudhary P. Data privacy and security in the banking sector: challenges and best practices. Issue 4 Int'l JL Mgmt Hum. 2023;6:1635. https://doij.org/10.10000/IJLMH.115613 . Buccafurri F, De Angelis V, Lazzaro S. A blockchain-based framework to enhance anonymous services with accountability guarantees. Future Internet. 2022;14(8):243. https://doi.org/10.3390/fi14080243 . Additional Declarations No competing interests reported. Supplementary Files ADuressEnabledMobileBankingSystemforCoercionResistantTransactionsSupplementaryfiles.docx Cite Share Download PDF Status: Under Review Version 1 posted Editorial decision: Revision requested 31 Mar, 2026 Reviews received at journal 29 Mar, 2026 Reviews received at journal 23 Mar, 2026 Reviews received at journal 12 Mar, 2026 Reviews received at journal 11 Mar, 2026 Reviewers agreed at journal 11 Mar, 2026 Reviewers agreed at journal 05 Mar, 2026 Reviewers agreed at journal 03 Mar, 2026 Reviewers agreed at journal 15 Jan, 2026 Reviewers agreed at journal 22 Dec, 2025 Reviewers invited by journal 22 Dec, 2025 Editor assigned by journal 09 Dec, 2025 Submission checks completed at journal 08 Dec, 2025 First submitted to journal 04 Dec, 2025 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-8279747","acceptedTermsAndConditions":true,"allowDirectSubmit":false,"archivedVersions":[],"articleType":"Research Article","associatedPublications":[],"authors":[{"id":564234296,"identity":"2eb2ac76-300b-4f50-921f-ca88279f9234","order_by":0,"name":"Idris Olanrewaju Ibraheem","email":"data:image/png;base64,iVBORw0KGgoAAAANSUhEUgAAAZAAAAAyAQMAAABI0h/eAAAABlBMVEX///8AAABVwtN+AAAACXBIWXMAAA7EAAAOxAGVKw4bAAABDUlEQVRIiWNgGAWjYBACNgkGBmYwi5nBgCGBwYYfzOEhQUuaZAMhLQxwLQxALQwMhwlr4ZPuffi5oMImmoGdeduHB3/OSxgcb2B88LaNIU/eAYfDZI4bS884k5bbwMxWPCOx7baEwZkDzIZz2xiKDQ/g8ksagzRv22GgFh5jhsSG23UGNxLYgCIMiRsbcGph/s377z9ES8KfcxJALey/CWgBmtlwAKqF7QBICxszSMt8HN5nkznGZs1zLDm3DegXhsS2ZAnJMwebJeeck0jcgEOL/Ow25ts8NXa5/fyHNzP++GMnwXe8+eCHN2U2ifNxOAxhHYLJCFIrwWBwgIAWLA4gZMsoGAWjYBSMFAAAf2NS6c/mLGQAAAAASUVORK5CYII=","orcid":"","institution":"Fountain University","correspondingAuthor":true,"prefix":"","firstName":"Idris","middleName":"Olanrewaju","lastName":"Ibraheem","suffix":""},{"id":564234297,"identity":"31f22f50-c182-4ba0-a4b9-ef2e805d3e9d","order_by":1,"name":"Muhammad Tijjani Jidda","email":"","orcid":"","institution":"Ahmadu Bello University","correspondingAuthor":false,"prefix":"","firstName":"Muhammad","middleName":"Tijjani","lastName":"Jidda","suffix":""}],"badges":[],"createdAt":"2025-12-04 13:23:05","currentVersionCode":1,"declarations":"","doi":"10.21203/rs.3.rs-8279747/v1","doiUrl":"https://doi.org/10.21203/rs.3.rs-8279747/v1","draftVersion":[],"editorialEvents":[],"editorialNote":"","failedWorkflow":false,"files":[{"id":98943412,"identity":"972627ea-ef62-4ca6-9d99-d77e245fb428","added_by":"auto","created_at":"2025-12-24 11:44:55","extension":"docx","order_by":0,"title":"","display":"","copyAsset":false,"role":"acdc-reference","size":275254,"visible":true,"origin":"","legend":"","description":"","filename":"ADuressEnabledMobileBankingSystemforCoercionResistantTransactionsmain4.docx","url":"https://assets-eu.researchsquare.com/files/rs-8279747/v1/e8d0a5cd6018d2fac51a48b2.docx"},{"id":98943409,"identity":"f4e6c8f8-6cf2-4dc6-87f8-ca4f3dc9aedf","added_by":"auto","created_at":"2025-12-24 11:44:55","extension":"json","order_by":1,"title":"","display":"","copyAsset":false,"role":"acdc-reference","size":4556,"visible":true,"origin":"","legend":"","description":"","filename":"2172a5ae6fe2412694d95fd6ef66a15a.json","url":"https://assets-eu.researchsquare.com/files/rs-8279747/v1/e85a78254fae3e28061a02b6.json"},{"id":98943417,"identity":"de9c57cb-f2dc-4990-baee-86853defffdb","added_by":"auto","created_at":"2025-12-24 11:44:55","extension":"docx","order_by":2,"title":"","display":"","copyAsset":false,"role":"acdc-reference","size":2370409,"visible":true,"origin":"","legend":"","description":"","filename":"ADuressEnabledMobileBankingSystemforCoercionResistantTransactionsSupplementaryfiles.docx","url":"https://assets-eu.researchsquare.com/files/rs-8279747/v1/0d308702443ded65321674f0.docx"},{"id":98943415,"identity":"445aee51-9624-4926-b675-c68a55fb0847","added_by":"auto","created_at":"2025-12-24 11:44:55","extension":"xml","order_by":3,"title":"","display":"","copyAsset":false,"role":"acdc-reference","size":112710,"visible":true,"origin":"","legend":"","description":"","filename":"2172a5ae6fe2412694d95fd6ef66a15a1enriched.xml","url":"https://assets-eu.researchsquare.com/files/rs-8279747/v1/9b92d9e483905cdd2ba8956a.xml"},{"id":99310643,"identity":"68cdbf02-91d7-4f3f-a232-d56124a48599","added_by":"auto","created_at":"2025-12-31 16:13:07","extension":"png","order_by":7,"title":"","display":"","copyAsset":false,"role":"acdc-reference","size":36959,"visible":true,"origin":"","legend":"","description":"","filename":"Onlinefloatimage1.png","url":"https://assets-eu.researchsquare.com/files/rs-8279747/v1/311b666900b64c564918dec2.png"},{"id":98943413,"identity":"62553906-1768-49f0-aabb-3e2b1338063f","added_by":"auto","created_at":"2025-12-24 11:44:55","extension":"png","order_by":8,"title":"","display":"","copyAsset":false,"role":"acdc-reference","size":27835,"visible":true,"origin":"","legend":"","description":"","filename":"Onlinefloatimage2.png","url":"https://assets-eu.researchsquare.com/files/rs-8279747/v1/05371a50bcbdd320def4879f.png"},{"id":99310709,"identity":"26c0d9ad-5b40-409a-9028-60c4abd56987","added_by":"auto","created_at":"2025-12-31 16:13:14","extension":"png","order_by":9,"title":"","display":"","copyAsset":false,"role":"acdc-reference","size":15003,"visible":true,"origin":"","legend":"","description":"","filename":"Onlinefloatimage3.png","url":"https://assets-eu.researchsquare.com/files/rs-8279747/v1/f3f880fcc04df0b5628d3d61.png"},{"id":98943420,"identity":"32ab322e-dfa7-4b08-a8b0-c1163033cd51","added_by":"auto","created_at":"2025-12-24 11:44:56","extension":"xml","order_by":10,"title":"","display":"","copyAsset":false,"role":"acdc-reference","size":110222,"visible":true,"origin":"","legend":"","description":"","filename":"2172a5ae6fe2412694d95fd6ef66a15a1structuring.xml","url":"https://assets-eu.researchsquare.com/files/rs-8279747/v1/0e953e2063b1d6b9af4d0397.xml"},{"id":99310793,"identity":"888efa58-8f0b-424c-b0b3-5bb08ce26348","added_by":"auto","created_at":"2025-12-31 16:13:23","extension":"html","order_by":11,"title":"","display":"","copyAsset":false,"role":"acdc-reference","size":122449,"visible":true,"origin":"","legend":"","description":"","filename":"earlyproof.html","url":"https://assets-eu.researchsquare.com/files/rs-8279747/v1/6b416f20aeac2d9f225f8f97.html"},{"id":98943408,"identity":"1d46adbb-2ac6-420b-8fda-ad91af13ecdb","added_by":"auto","created_at":"2025-12-24 11:44:55","extension":"png","order_by":1,"title":"Figure 1","display":"","copyAsset":false,"role":"figure","size":112209,"visible":true,"origin":"","legend":"\u003cp\u003eLegend not included with this version.\u003c/p\u003e","description":"","filename":"floatimage1.png","url":"https://assets-eu.researchsquare.com/files/rs-8279747/v1/88fa795bf8174ab6a3bbe3d4.png"},{"id":98943414,"identity":"a03cba0a-166a-4597-8952-f55fe550a6cf","added_by":"auto","created_at":"2025-12-24 11:44:55","extension":"png","order_by":2,"title":"Figure 2","display":"","copyAsset":false,"role":"figure","size":76292,"visible":true,"origin":"","legend":"\u003cp\u003eLegend not included with this version.\u003c/p\u003e","description":"","filename":"floatimage2.png","url":"https://assets-eu.researchsquare.com/files/rs-8279747/v1/7d81326bfbdfe2954e1822f0.png"},{"id":98943411,"identity":"400d62d5-ef9f-4400-9175-6247807c7724","added_by":"auto","created_at":"2025-12-24 11:44:55","extension":"png","order_by":3,"title":"Figure 3","display":"","copyAsset":false,"role":"figure","size":60621,"visible":true,"origin":"","legend":"\u003cp\u003eLegend not included with this version.\u003c/p\u003e","description":"","filename":"floatimage3.png","url":"https://assets-eu.researchsquare.com/files/rs-8279747/v1/aa5c4af97c7bdf7280646df5.png"},{"id":100356217,"identity":"ba28c17c-b9f3-4f30-8605-549844ed050f","added_by":"auto","created_at":"2026-01-16 06:57:42","extension":"pdf","order_by":0,"title":"","display":"","copyAsset":false,"role":"manuscript-pdf","size":1413653,"visible":true,"origin":"","legend":"","description":"","filename":"manuscript.pdf","url":"https://assets-eu.researchsquare.com/files/rs-8279747/v1/764eb234-c9ea-421d-9d53-18c73a9e0c53.pdf"},{"id":98943419,"identity":"e28e766f-7253-47b2-810f-7a68f4126959","added_by":"auto","created_at":"2025-12-24 11:44:55","extension":"docx","order_by":0,"title":"","display":"","copyAsset":false,"role":"supplement","size":2370409,"visible":true,"origin":"","legend":"","description":"","filename":"ADuressEnabledMobileBankingSystemforCoercionResistantTransactionsSupplementaryfiles.docx","url":"https://assets-eu.researchsquare.com/files/rs-8279747/v1/b0bc57a0404f5e7a5827f543.docx"}],"financialInterests":"No competing interests reported.","formattedTitle":"A Duress-Enabled Mobile Banking System for Coercion-Resistant Transactions","fulltext":[{"header":"1. Introduction","content":"\u003cp\u003eThe increasing exploitation of criminals and abusers of mobile banking\u0026rsquo;s immediacy, with an attacker coercing victims to authenticate and transfer funds from a smartphone or ATM, leaves the victims with immediate financial loss and long-term credit damage. Policy makers and regulators have recently recognized coerced debt and forced financial transactions as a growing social and consumer-protection problem that banks must address.\u003c/p\u003e \u003cp\u003eModern smartphones with secure push-message capabilities, tamper-evident logging that could leverage blockchain, and advanced fraud-detection pipelines create new opportunities. Recent research has demonstrated that blockchain-based forensic logging with strong access control and immutable audit trails can reliably store and protect log data against tampering [\u003cspan citationid=\"CR1\" class=\"CitationRef\"\u003e1\u003c/span\u003e]. This opens the possibility for banks to adopt covert duress modes: transactions may appear to succeed normally to an attacker, yet are logged immutably, quarantined for review, and remain traceable for recovery and legal investigation [\u003cspan citationid=\"CR2\" class=\"CitationRef\"\u003e2\u003c/span\u003e].\u003c/p\u003e \u003cp\u003eThe introduction of a duress mode also introduces abuse risks that can also bring about false claims, collusion, and vendor scams. And legal/regulatory issues (funds availability, AML obligations, privacy). Any usable solution must balance immediate safety (minimize victim harm), traceability for recovery and law enforcement, minimal cognitive burden under stress, and abuse-resistance through process and analytics. Recent coercion-resistance research in adjacent fields (data storage, e-voting) shows design patterns and human-factors traps that are directly relevant [\u003cspan citationid=\"CR3\" class=\"CitationRef\"\u003e3\u003c/span\u003e].\u003c/p\u003e \u003cp\u003eThis study will design a duress-aware transaction model that includes a duress PIN and duress-login modes, a prototype a mobile app\u0026thinsp;+\u0026thinsp;backend with quarantine/forensic tagging and covert alerts, evaluate security though threat modeling and red-team scenarios, usability under stress (human factors study), and economic/legal implications for recovery, and lastly, propose operational policies and abuse-mitigation strategies for banks and regulators.\u003c/p\u003e \u003cdiv id=\"Sec2\" class=\"Section2\"\u003e \u003ch2\u003e1.1 Problem statement\u003c/h2\u003e \u003cp\u003eVictims of physical coercion who are forced to authorize otherwise valid financial transactions lack reliable, standard technical and operational mechanisms that allow the transaction to proceed without immediate harm, while limiting the attacker\u0026rsquo;s ability to profit and leaving strong, tamper-evident forensic markers that enable timely recovery and investigation. Design, implementation, and evaluation of a duress-aware mobile banking framework that addresses the gaps from the previous study.\u003c/p\u003e \u003c/div\u003e \u003cdiv id=\"Sec3\" class=\"Section2\"\u003e \u003ch2\u003e1.2 Objectives\u003c/h2\u003e \u003cp\u003eFormalize a threat model for coercion in mobile banking.\u003c/p\u003e \u003cp\u003eDesign covert authentication modes (duress PIN and login).\u003c/p\u003e \u003cp\u003eDevelop secure backend mechanisms with escrow and immutable logging.\u003c/p\u003e \u003cp\u003eImplementation and evaluation of a proof-of-concept system with security, usability, and regulatory analysis.\u003c/p\u003e \u003c/div\u003e \u003cdiv id=\"Sec4\" class=\"Section2\"\u003e \u003ch2\u003e1.3 Contributions of the study\u003c/h2\u003e \u003cp\u003eThis study makes several key contributions to advancing secure and resilient mobile banking systems. The introduction of a formal threat model for physical coercion captures the attacker's capabilities, the user's constraints, and the system's trust boundaries. Based on this model, the study proposes a duress-aware transaction framework that incorporates both duress PINs and duress logins, with transfer restrictions, covert alerting, and embedded forensic markers. A prototype of the system, comprising a mobile application, backend services, and tamper-evident logging, was developed alongside an adaptable API specification for banking institutions. The study further shows the evaluated results from security analyses, simulated transaction experiments, and a human-subjects usability study, demonstrating the system\u0026rsquo;s effectiveness and practicality under stress. In addition, it offers operational and policy guidance, including recommended SOPs for banks, abuse-mitigation strategies, and insights into anti-money laundering and regulatory trade-offs. Finally, it contributes a reproducible dataset and experiment scripts, enabling future researchers to conduct synthetic transaction simulations and test related duress-aware designs. Below are some of the integrated options that can also be improved.\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 2\u003c/div\u003e \u003cdiv class=\"CaptionContent\"\u003e \u003cp\u003eFeature Options Between Traditional Banking and Duress Banking Framework\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\u003eFeature/Aspect\u003c/p\u003e \u003c/th\u003e \u003cth align=\"left\" colname=\"c2\"\u003e \u003cp\u003eTraditional Banking Security\u003c/p\u003e \u003c/th\u003e \u003cth align=\"left\" colname=\"c3\"\u003e \u003cp\u003eDuress Banking Authentication System\u003c/p\u003e \u003c/th\u003e \u003c/tr\u003e \u003c/thead\u003e \u003ctbody\u003e \u003ctr\u003e \u003ctd align=\"left\" colname=\"c1\"\u003e \u003cp\u003e\u003cb\u003eAuthentication Method\u003c/b\u003e\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c2\"\u003e \u003cp\u003ePINs, passwords, biometrics\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c3\"\u003e \u003cp\u003ePIN/biometric with hidden duress signal\u003c/p\u003e \u003c/td\u003e \u003c/tr\u003e \u003ctr\u003e \u003ctd align=\"left\" colname=\"c1\"\u003e \u003cp\u003e\u003cb\u003eUser Safety Under Coercion\u003c/b\u003e\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c2\"\u003e \u003cp\u003eVulnerable (no covert alert)\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c3\"\u003e \u003cp\u003eProvides covert distress signaling\u003c/p\u003e \u003c/td\u003e \u003c/tr\u003e \u003ctr\u003e \u003ctd align=\"left\" colname=\"c1\"\u003e \u003cp\u003e\u003cb\u003eDetection of Forced Transactions\u003c/b\u003e\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c2\"\u003e \u003cp\u003eAbsent\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c3\"\u003e \u003cp\u003eBuilt-in duress flagging mechanism\u003c/p\u003e \u003c/td\u003e \u003c/tr\u003e \u003ctr\u003e \u003ctd align=\"left\" colname=\"c1\"\u003e \u003cp\u003e\u003cb\u003eIntegration with SOC/SIEM\u003c/b\u003e\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c2\"\u003e \u003cp\u003eLimited\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c3\"\u003e \u003cp\u003eDirect integration for real-time alerts\u003c/p\u003e \u003c/td\u003e \u003c/tr\u003e \u003ctr\u003e \u003ctd align=\"left\" colname=\"c1\"\u003e \u003cp\u003e\u003cb\u003eAnomaly Detection\u003c/b\u003e\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c2\"\u003e \u003cp\u003eBasic rule-based fraud checks\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c3\"\u003e \u003cp\u003eAI-enhanced anomaly \u0026amp; behavioral analysis\u003c/p\u003e \u003c/td\u003e \u003c/tr\u003e \u003ctr\u003e \u003ctd align=\"left\" colname=\"c1\"\u003e \u003cp\u003e\u003cb\u003eCustomer Trust\u003c/b\u003e\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c2\"\u003e \u003cp\u003eModerate (risk of coercion remains)\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c3\"\u003e \u003cp\u003eEnhanced trust due to proactive safety\u003c/p\u003e \u003c/td\u003e \u003c/tr\u003e \u003ctr\u003e \u003ctd align=\"left\" colname=\"c1\"\u003e \u003cp\u003e\u003cb\u003eImplementation Complexity\u003c/b\u003e\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c2\"\u003e \u003cp\u003eLow to moderate\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c3\"\u003e \u003cp\u003eModerate to high (requires AI\u0026thinsp;+\u0026thinsp;secure logging)\u003c/p\u003e \u003c/td\u003e \u003c/tr\u003e \u003ctr\u003e \u003ctd align=\"left\" colname=\"c1\"\u003e \u003cp\u003e\u003cb\u003eRegulatory Alignment\u003c/b\u003e\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c2\"\u003e \u003cp\u003eStandard compliance\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c3\"\u003e \u003cp\u003eRequires new frameworks for covert alert handling\u003c/p\u003e \u003c/td\u003e \u003c/tr\u003e \u003c/tbody\u003e \u003c/colgroup\u003e \u003c/table\u003e\u003c/div\u003e \u003c/p\u003e \u003c/div\u003e"},{"header":"2. Literature Review","content":"\u003cp\u003eExtended research on the intersection of artificial intelligence (AI), machine learning (ML), and financial cybersecurity has grown in recent years, where various applications ranging from fraud prevention to anomaly detection in digital banking. Scholars have increasingly emphasized the vulnerabilities of mobile banking systems and online payment infrastructures as usage grows globally, particularly in developing regions where financial inclusion efforts have accelerated [\u003cspan citationid=\"CR2\" class=\"CitationRef\"\u003e2\u003c/span\u003e]. This has heightened the urgency of frameworks capable of addressing unique, high-risk scenarios such as duress banking, where users are compelled to perform transactions under coercion.\u003c/p\u003e \u003cdiv id=\"Sec6\" class=\"Section2\"\u003e \u003ch2\u003e2.1 Authentication and Duress Security\u003c/h2\u003e \u003cp\u003eAuthentication remains the cornerstone of mobile banking security. The traditional authentication methods, such as PINs, passwords, and biometric verification methods, dominate, but these methods assume user consent. In a study conducted by [\u003cspan citationid=\"CR3\" class=\"CitationRef\"\u003e3\u003c/span\u003e], they analyzed adaptive multi-factor authentication in mobile banking, which shows improvements in the prevention of unauthorized access. Although multi-factor systems still fail under coercion, as attackers can force users to comply. [\u003cspan citationid=\"CR4\" class=\"CitationRef\"\u003e4\u003c/span\u003e] emphasized usable security, noting that overly complex authentication harms adoption. The proposed duress PIN/login aligns with these usability principles, as it mirrors normal input but covertly activates a protective protocol.\u003c/p\u003e \u003cp\u003eThere has been a tremendous evolution in the field of user authentication, most notably with the adoption of behavioral biometrics. Recent studies, such as the one conducted by [\u003cspan citationid=\"CR5\" class=\"CitationRef\"\u003e5\u003c/span\u003e], explored gait recognition, keystroke dynamics, and mouse movement patterns as pointers for user intent. While it is established that biometric systems provide enhanced security, their primary focus is mostly on the prevention of unauthorized access rather than identifying situations where an authorized user is under external pressure. This limitation reiterates the novelty of addressing duress in banking operations.\u003c/p\u003e \u003cp\u003eResearch into covert authentication mechanisms has been limited. [\u003cspan citationid=\"CR6\" class=\"CitationRef\"\u003e6\u003c/span\u003e] explored silent emergency signaling through mobile devices, demonstrating that users could discreetly activate alerts in hostage situations. Extending this to banking, our duress PIN/login functions as a dual-purpose mechanism: satisfying the coercer\u0026rsquo;s demand while signaling distress to the bank. There is literature that focuses on fraud prevention through the lens of behavioural biometrics, where user interaction patterns such as touchscreen pressure, keystroke dynamics, and navigation flows are monitored to detect deviations that indicate fraud or coercion. In a study conducted by [\u003cspan citationid=\"CR7\" class=\"CitationRef\"\u003e7\u003c/span\u003e], they proposed a governance-centric model integrating behavioural biometrics into intelligent fraud prevention, emphasizing the balance between accuracy, privacy, and compliance. Similarly, [\u003cspan citationid=\"CR8\" class=\"CitationRef\"\u003e8\u003c/span\u003e] advanced AI-powered behavioural biometric methods, highlighting their potential for next-generation financial cybersecurity. These contributions show that banking security is shifting toward continuous authentication, a principle directly relevant for duress detection.\u003c/p\u003e \u003cp\u003eAn earlier study carried out by [\u003cspan citationid=\"CR9\" class=\"CitationRef\"\u003e9\u003c/span\u003e] shows how behavioural biometrics significantly improve security in mobile banking applications, reducing reliance on static credentials such as PINs and passwords. Their study highlights the feasibility of implementing non-intrusive background authentication mechanisms that can flag unusual patterns, an approach that can be extended to identifying signals of user stress under coercion. However, SMS-based OTPs, which are traditional methods, remain vulnerable to social engineering and coercion, which shows the need for duress-aware mechanisms.\u003c/p\u003e \u003c/div\u003e \u003cdiv id=\"Sec7\" class=\"Section2\"\u003e \u003ch2\u003e2.2 Fraud Detection and Anomaly Recognition\u003c/h2\u003e \u003cp\u003eFraud detection has received considerable attention by leveraging the capabilities of AI and machine learning, offering robust tools for identifying suspicious activity. [\u003cspan citationid=\"CR10\" class=\"CitationRef\"\u003e10\u003c/span\u003e] proposed an AI-based anomaly detection approach for mobile banking transactions, resulting in improved fraud prevention. In a similar study by [\u003cspan citationid=\"CR11\" class=\"CitationRef\"\u003e11\u003c/span\u003e], Artificial intelligence (AI) enhances fraud detection in cloud-based cryptocurrency platforms by analyzing transactions in real time to identify suspicious patterns and anomalies. This strengthens the Anti-Money Laundering (AML) and Know Your Customer (KYC) protocols with improved identity verification. However, deepfake technology and synthetic identity fraud, which are emerging threats, require advanced AI-driven solutions such as biometric authentication and fraud detection tools to maintain security. Similarly, [\u003cspan citationid=\"CR12\" class=\"CitationRef\"\u003e12\u003c/span\u003e] in their study showed the vulnerabilities in digital payments and stressed the importance of transaction reversibility. Yet, both approaches rely on identifying abnormal behavior. In coercion scenarios, transactions appear entirely normally initiated by the rightful account holder. This limitation indicates the need for duress-aware systems that embed proactive safeguards.\u003c/p\u003e \u003cp\u003eSome studies conducted on anomaly detection have played a critical role in advancing security measures across financial services. [\u003cspan citationid=\"CR13\" class=\"CitationRef\"\u003e13\u003c/span\u003e] emphasized the importance of adaptive learning to manage evolving threats in network and banking environments. These contributions reiterate the foundation for including the anomaly detection process into duress banking frameworks, where behavioral deviations can indicate coercion.\u003c/p\u003e \u003cp\u003eThe vulnerabilities of mobile banking systems in the growing markets remain a significant concern. In a study conducted by [\u003cspan citationid=\"CR14\" class=\"CitationRef\"\u003e14\u003c/span\u003e], they performed a security evaluation of Nigerian mobile banking apps. Through the evaluation, they uncovered weak encryption, inadequate fraud controls, and poor session management. These findings show the need for context-specific solutions like duress banking, especially in countries where armed robbery and coercive withdrawals are common. The integration of duress features directly into app design could address local security threats while still being in alignment with global banking security standards.\u003c/p\u003e \u003cp\u003eFraud in digital transactions has also been studied from a systemic perspective. [\u003cspan citationid=\"CR15\" class=\"CitationRef\"\u003e15\u003c/span\u003e] In their research presented anomaly detection and risk management in online payment systems, showing the role of ML models in balancing fraud prevention while minimizing false positives. They argued that effective detection frameworks should have a combination of supervised and unsupervised methods to handle evolving attack vectors. The implications this would have on duress banking are that anomaly detection could serve as a backend verification layer, using it for the confirmation of transactions if they align with typical behaviour, flagging potential duress situations for intervention.\u003c/p\u003e \u003cp\u003eIn a systematic review study conducted by [\u003cspan citationid=\"CR17\" class=\"CitationRef\"\u003e17\u003c/span\u003e], they reviewed cybersecurity threats in digital financial services, observing a rising sophistication in attack vectors. They noted that while anomaly detection tools evolve, attackers adapt equally quickly. The proposed framework moves beyond anomaly detection through the provision of an invisible layer of user safety, which attackers cannot detect without previous knowledge of the duress pathway.\u003c/p\u003e \u003c/div\u003e \u003cdiv id=\"Sec8\" class=\"Section2\"\u003e \u003ch2\u003e2.3 Usable Security and Human-Centered Design\u003c/h2\u003e \u003cp\u003eDesigning security mechanisms that users can adopt in real-world scenarios is critical. [\u003cspan citationid=\"CR4\" class=\"CitationRef\"\u003e4\u003c/span\u003e] argued in their study that security must be both strong and usable. However, a system that comes with a lot of burden reduces compliance and encourages risky workarounds. The duress PIN/login proposed in this study leverages a familiar input pattern, ensuring that users under duress can activate it without hesitation or error.\u003c/p\u003e \u003cp\u003eIn research carried out by [\u003cspan citationid=\"CR18\" class=\"CitationRef\"\u003e18\u003c/span\u003e], which studied user experience in mobile payment systems, the outcome of which revealed that perceived safety plays a huge role in the adoption of certain payment systems. In regions where crime rates are high, trust in digital banking declines without visible safeguards. By visibly promoting duress features while keeping their activation covert, banks can rebuild trust and confidence among customers.\u003c/p\u003e \u003cp\u003eFrom a usability standpoint, studies have shown the tension between security and user convenience. [\u003cspan citationid=\"CR19\" class=\"CitationRef\"\u003e19\u003c/span\u003e] examined mobile banking security features and concluded that overly complex security steps reduce adoption, particularly among older or less-tech-savvy users. This challenge is relevant to duress banking, where any added security layer must remain unobtrusive during normal use but seamlessly activated under coercion. [\u003cspan citationid=\"CR7\" class=\"CitationRef\"\u003e7\u003c/span\u003e] further emphasized that user-centric design plays a key role in adoption, as poorly integrated features can generate mistrust and disengagement.\u003c/p\u003e \u003c/div\u003e \u003cdiv id=\"Sec9\" class=\"Section2\"\u003e \u003ch2\u003e2.4 Financial Crime and Coercion Risks\u003c/h2\u003e \u003cp\u003eResearch on coercive financial crimes remains sparse, but studies highlight growing concern. A recent study by [\u003cspan citationid=\"CR20\" class=\"CitationRef\"\u003e20\u003c/span\u003e] examined Nigeria\u0026rsquo;s cashless policy, noting that while digital adoption increased, so did coercive financial crimes. Similar concerns have echoed globally, where attackers shift focus from ATM robberies to mobile app coercion. In a study by [\u003cspan citationid=\"CR21\" class=\"CitationRef\"\u003e21\u003c/span\u003e], fintech risks in Africa were discussed, emphasizing that regulatory frameworks often lag behind technological innovation. The proposed duress banking model complements regulation by embedding preventive measures at the system level, reducing reliance on after-the-fact legal recourse.\u003c/p\u003e \u003cp\u003eStudies have also shown the role of psychological and physiological patterns in coercion detection. While financial technology research has not yet fully embraced these methods, studies in human\u0026ndash;computer interaction suggest that stress signals such as hesitations, unusual gesture pressure, and rapid eye movement patterns could be detectable by AI systems [\u003cspan citationid=\"CR22\" class=\"CitationRef\"\u003e22\u003c/span\u003e][\u003cspan citationid=\"CR23\" class=\"CitationRef\"\u003e23\u003c/span\u003e]. Applying these insights to duress banking could open new avenues for covert stress detection, strengthening resilience against physical coercion attacks. [\u003cspan citationid=\"CR24\" class=\"CitationRef\"\u003e24\u003c/span\u003e] explored financial consumer protection in digital contexts, stressing the need for proactive safety features. Their findings are in line with the objective of this research that banks must move beyond fraud prevention to human-centered protection, where safety under coercion is prioritized.\u003c/p\u003e \u003cp\u003e \u003cb\u003eBlockchain as a tool\u003c/b\u003e \u003c/p\u003e \u003cp\u003eBlockchain is now viewed as a complementary tool in securing banking transactions. Work by [\u003cspan citationid=\"CR25\" class=\"CitationRef\"\u003e25\u003c/span\u003e][\u003cspan citationid=\"CR26\" class=\"CitationRef\"\u003e26\u003c/span\u003e] showed that immutability of blockchain systems provides a tamper-proof record of transactions, ensuring accountability and transparency in financial operations. When combined with AI-driven monitoring systems, blockchain offers a powerful mechanism for logging potential duress-triggered activities in a secure and auditable manner. This synergy provides a foundation for secure and accountable duress reporting without compromising user safety.\u003c/p\u003e \u003c/div\u003e \u003cdiv id=\"Sec10\" class=\"Section2\"\u003e \u003ch2\u003e2.5 Emergency Signaling and Covert Systems\u003c/h2\u003e \u003cp\u003eEmergency signaling has been studied in security-sensitive contexts. [\u003cspan citationid=\"CR6\" class=\"CitationRef\"\u003e6\u003c/span\u003e] demonstrated that covert alerts in mobile systems can aid in hostage rescue. [\u003cspan citationid=\"CR27\" class=\"CitationRef\"\u003e27\u003c/span\u003e] investigated the use of wearable devices for psychological monitoring of silent emergency signaling, showing feasibility for real-time distress communication. Translating these ideas into banking, our framework introduces financial distress signaling, where duress-triggered transactions automatically alert the bank while masking critical account information.\u003c/p\u003e \u003cp\u003eSimilarly, recent research demonstrates significant advances in IoT-based hidden distress systems for personal safety, particularly targeting women's security concerns. These systems integrate multiple sensors, including heart rate monitors, accelerometers, GPS modules, and microphones, within wearable devices to enable continuous, discreet monitoring [\u003cspan citationid=\"CR28\" class=\"CitationRef\"\u003e28\u003c/span\u003e][\u003cspan citationid=\"CR29\" class=\"CitationRef\"\u003e29\u003c/span\u003e]. This proposed system adapts these principles into financial ecosystems, creating a dual-protection layer: safeguarding both human life and financial assets.\u003c/p\u003e \u003cp\u003e \u003cb\u003eThe Role of AI in the Elimination of Duress-Coercion Frauds\u003c/b\u003e \u003c/p\u003e \u003cp\u003eIn recent years, the rise of explainable AI (XAI) has become a key focus in financial security applications. [\u003cspan citationid=\"CR30\" class=\"CitationRef\"\u003e30\u003c/span\u003e] emphasized that explainability is crucial for building trust in automated decision-making, especially in regulated industries like banking. [\u003cspan citationid=\"CR31\" class=\"CitationRef\"\u003e31\u003c/span\u003e] demonstrated that combining interpretable models with anomaly detection systems enables institutions to justify their interventions in real-time. When applied to duress banking, explainability guarantees that actions such as freezing an account or flagging a transaction are both legally defensible and operationally transparent.\u003c/p\u003e \u003cp\u003eIn addition, regulatory and ethical considerations have received growing attention. AI-driven fraud detection usually requires more data collection, which raises privacy concerns under frameworks such as the General Data Protection Regulation (GDPR) and Nigeria\u0026rsquo;s Data Protection Act [\u003cspan citationid=\"CR32\" class=\"CitationRef\"\u003e32\u003c/span\u003e]. Duress banking must therefore be designed to ensure compliance with privacy regulations while still providing law enforcement or financial institutions with actionable alerts [\u003cspan citationid=\"CR33\" class=\"CitationRef\"\u003e33\u003c/span\u003e]. The pressure between anonymity and accountability represents a fundamental challenge in digital systems, particularly in blockchain and digital currency applications. [\u003cspan citationid=\"CR34\" class=\"CitationRef\"\u003e34\u003c/span\u003e] address this trade-off by proposing a blockchain-based framework that requires collaboration among three independent parties to disclose user identities, ensuring anonymity is maintained unless all parties agree to reveal identity for accountability purposes.\u003c/p\u003e \u003cp\u003eDespite this progress, a consistent theme in previous literature is the lack of focus on duress detection as a clear research problem. Existing works treat anomalies in a broad manner, encompassing fraud, insider threats, or system-level intrusions without addressing coercion scenarios where transactions are seemingly legitimate but initiated under pressure. The proposed study bridges this gap through the combination of AI-driven anomaly detection, behavioral biometrics, and blockchain-secured logging to develop a novel duress banking framework. In doing so, it not only extends prior works in intrusion detection and fraud prevention but also pioneers a practical and socially impactful domain in financial security.\u003c/p\u003e \u003c/div\u003e"},{"header":"3. Research Methodology","content":"\u003cdiv id=\"Sec12\" class=\"Section2\"\u003e \u003ch2\u003e3.1 Research Design\u003c/h2\u003e \u003cp\u003eThis study adopts a design science research methodology (DSRM), which is suitable for developing and evaluating innovative technological output aimed at solving practical problems in banking security. The system will be designed as a mobile banking application enhancement that incorporates a duress function through PIN and password variations. The design will follow iterative prototyping, user-centered design principles, and security testing in simulated environments.\u003c/p\u003e \u003cp\u003e \u003c/p\u003e \u003cp\u003eFlowchart of Duress Banking System\u003c/p\u003e \u003c/div\u003e \u003cdiv id=\"Sec13\" class=\"Section2\"\u003e \u003ch2\u003e3.2 System Architecture\u003c/h2\u003e \u003cp\u003eThe proposed system architecture, as shown in Fig.\u0026nbsp;2, integrates the duress functionality into the authentication and transaction processing layers of mobile banking platforms. The authentication module will accept two categories of credentials. A normal PIN/password for regular use and a duress PIN/password for emergency use. When a duress credential is entered, the system will initiate a modified transaction workflow, which enables funds transfer but embeds tracking, monitoring, and restrictions. A middleware layer will enforce constraints such as limiting the transaction value, restricting cash withdrawals, and logging the event to a secure monitoring server [\u003cspan citationid=\"CR27\" class=\"CitationRef\"\u003e27\u003c/span\u003e].\u003c/p\u003e \u003cp\u003eFigure\u0026nbsp;\u003cspan refid=\"Fig1\" class=\"InternalRef\"\u003e1\u003c/span\u003e\u003c/p\u003e \u003cp\u003e \u003c/p\u003e \u003cp\u003eSystem Architecture for Duress Transaction Handling in Banking\u003c/p\u003e \u003c/div\u003e \u003cdiv id=\"Sec14\" class=\"Section2\"\u003e \u003ch2\u003e4.3 Duress PIN and Duress Login Mechanism\u003c/h2\u003e \u003cp\u003eThe duress PIN system ensures that when a customer is coerced, they can still perform a transaction under duress without alerting the attacker. The transaction will appear normal from the attacker\u0026rsquo;s perspective, but will be flagged as duress at the backend. Similarly, a duress login will restrict account visibility by showing only a partial balance (e.g., 10%) and enabling only limited transactions. This layered design reduces the incentive for attackers to demand full account depletion while simultaneously alerting the bank\u0026rsquo;s fraud detection unit.\u003c/p\u003e \u003c/div\u003e \u003cdiv id=\"Sec15\" class=\"Section2\"\u003e \u003ch2\u003e4.4 Transaction Constraints and Monitoring\u003c/h2\u003e \u003cp\u003eTo prevent abuse, duress transactions will be restricted to interbank transfers only, excluding ATM withdrawals, point-of-sale purchases, or mobile money cash-outs. The system will also enforce transaction ceilings (e.g., 20% of account balance or a fixed threshold). Once triggered, duress transactions will automatically notify the bank\u0026rsquo;s risk management center and generate logs for further investigation. These constraints are consistent with financial security recommendations emphasizing multi-layered defense mechanisms.\u003c/p\u003e \u003c/div\u003e \u003cdiv id=\"Sec16\" class=\"Section2\"\u003e \u003ch2\u003e4.5 Data Security and Tracking Protocols\u003c/h2\u003e \u003cp\u003eAll duress-triggered transfers will embed traceable digital signatures and be routed exclusively through verifiable interbank channels. This design ensures that illicitly coerced funds remain within traceable systems, facilitating recovery upon customer complaints. Advanced end-to-end encryption (E2EE) and blockchain-inspired immutable logs will be integrated to guarantee transparency and non-repudiation. The system will also incorporate AI-based anomaly detection to differentiate genuine duress activations from misuse attempts.\u003c/p\u003e \u003c/div\u003e \u003cdiv id=\"Sec17\" class=\"Section2\"\u003e \u003ch2\u003e4.6 Misuse Prevention and Fraud Safeguards\u003c/h2\u003e \u003cp\u003eOne concern is that customers might misuse the duress feature to defraud vendors by claiming coercion after voluntary payments. To mitigate this, the inclusion of post-incident verification protocols in the system is required, such as voice biometrics, behavioral authentication logs, and geolocation data at the time of transaction. Machine learning algorithms will cross-check transaction contexts with duress patterns to minimize false claims.\u003c/p\u003e \u003c/div\u003e \u003cdiv id=\"Sec18\" class=\"Section2\"\u003e \u003ch2\u003e4.7 Simulation and Testing Environment\u003c/h2\u003e \u003cp\u003eThe proposed system will be tested in a controlled banking simulation environment using anonymized financial transaction datasets. Simulation scenarios will include coercion at gunpoint, voluntary fraud attempt by the customer, and accidental entry of duress credentials. The following metrics: transaction accuracy, false positive rate, system response time, and detection rate will be evaluated. These tests will establish the practicality and robustness of the design before pilot deployment.\u003c/p\u003e \u003c/div\u003e \u003cdiv id=\"Sec19\" class=\"Section2\"\u003e \u003ch2\u003e4.8 Ethical and Legal Considerations\u003c/h2\u003e \u003cp\u003eThe design will comply with Central Bank of Nigeria (CBN) digital banking guidelines and international data protection standards (GDPR, ISO/IEC 27001). Ethical considerations include balancing user safety with fraud prevention, ensuring user consent for biometric data use, and providing transparent disclosure of duress features. Collaborations with financial regulators will be necessary to define legal accountability frameworks for disputed transactions.\u003c/p\u003e \u003c/div\u003e \u003cdiv id=\"Sec20\" class=\"Section2\"\u003e \u003ch2\u003e4.9 Implementation Roadmap\u003c/h2\u003e \u003cp\u003eImplementation will proceed in three phases: (1) Prototype development using a mobile banking app simulator, (2) pilot testing with a selected group of users and financial institutions, and (3) Recommendation to financial institutions. Continuous monitoring and feedback will refine usability and security mechanisms. Future extensions may include biometric duress triggers (e.g., stress-based voice patterns, tremor detection on touchscreens) for enhanced covert signaling.\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\u003eSystem Architecture Based on Components and Functions\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\u003eLayer\u003c/p\u003e \u003c/th\u003e \u003cth align=\"left\" colname=\"c2\"\u003e \u003cp\u003eComponent\u003c/p\u003e \u003c/th\u003e \u003cth align=\"left\" colname=\"c3\"\u003e \u003cp\u003eFunction\u003c/p\u003e \u003c/th\u003e \u003c/tr\u003e \u003c/thead\u003e \u003ctbody\u003e \u003ctr\u003e \u003ctd align=\"left\" colname=\"c1\"\u003e \u003cp\u003e\u003cb\u003eUser Interface Layer\u003c/b\u003e\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c2\"\u003e \u003cp\u003eMobile Banking App (UI)\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c3\"\u003e \u003cp\u003eAccepts normal PIN/password or duress PIN/password during login/transactions.\u003c/p\u003e \u003c/td\u003e \u003c/tr\u003e \u003ctr\u003e \u003ctd align=\"left\" colname=\"c1\"\u003e \u003cp\u003e\u003cb\u003eAuthentication Layer\u003c/b\u003e\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c2\"\u003e \u003cp\u003eCredential Verifier\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c3\"\u003e \u003cp\u003eValidates whether the input is normal or duress credentials.\u003c/p\u003e \u003c/td\u003e \u003c/tr\u003e \u003ctr\u003e \u003ctd align=\"left\" colname=\"c1\"\u003e \u003cp\u003e\u003cb\u003eTransaction Control Layer\u003c/b\u003e\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c2\"\u003e \u003cp\u003eNormal Transaction Module\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c3\"\u003e \u003cp\u003eProcesses standard banking transactions without restrictions.\u003c/p\u003e \u003c/td\u003e \u003c/tr\u003e \u003ctr\u003e \u003ctd align=\"left\" colname=\"c1\"\u003e\u0026nbsp;\u003c/td\u003e \u003ctd align=\"left\" colname=\"c2\"\u003e \u003cp\u003eDuress Transaction Module\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c3\"\u003e \u003cp\u003eProcesses transactions under duress with constraints (limited amount, no cash withdrawal, partial balance display).\u003c/p\u003e \u003c/td\u003e \u003c/tr\u003e \u003ctr\u003e \u003ctd align=\"left\" colname=\"c1\"\u003e \u003cp\u003e\u003cb\u003eMonitoring \u0026amp; Security Layer\u003c/b\u003e\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c2\"\u003e \u003cp\u003eRisk Monitoring Engine\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c3\"\u003e \u003cp\u003eFlags duress transactions, notifies the bank\u0026rsquo;s security team, and logs events.\u003c/p\u003e \u003c/td\u003e \u003c/tr\u003e \u003ctr\u003e \u003ctd align=\"left\" colname=\"c1\"\u003e\u0026nbsp;\u003c/td\u003e \u003ctd align=\"left\" colname=\"c2\"\u003e \u003cp\u003eFraud Prevention Module\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c3\"\u003e \u003cp\u003ePrevents misuse through behavioral analysis, AI anomaly detection, and geolocation checks.\u003c/p\u003e \u003c/td\u003e \u003c/tr\u003e \u003ctr\u003e \u003ctd align=\"left\" colname=\"c1\"\u003e \u003cp\u003e\u003cb\u003eData \u0026amp; Logging Layer\u003c/b\u003e\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c2\"\u003e \u003cp\u003eSecure Ledger (Blockchain-inspired)\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c3\"\u003e \u003cp\u003eStores immutable transaction logs with traceable signatures.\u003c/p\u003e \u003c/td\u003e \u003c/tr\u003e \u003ctr\u003e \u003ctd align=\"left\" colname=\"c1\"\u003e \u003cp\u003e\u003cb\u003eIntegration Layer\u003c/b\u003e\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c2\"\u003e \u003cp\u003eInterbank Transfer Gateway\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c3\"\u003e \u003cp\u003eRoutes duress transactions only through verified bank-to-bank channels.\u003c/p\u003e \u003c/td\u003e \u003c/tr\u003e \u003ctr\u003e \u003ctd align=\"left\" colname=\"c1\"\u003e \u003cp\u003e\u003cb\u003eAdministration Layer\u003c/b\u003e\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c2\"\u003e \u003cp\u003eBank Risk Management Dashboard\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c3\"\u003e \u003cp\u003eAllows monitoring, alerts, and investigation of duress transactions.\u003c/p\u003e \u003c/td\u003e \u003c/tr\u003e \u003c/tbody\u003e \u003c/colgroup\u003e \u003c/table\u003e\u003c/div\u003e \u003c/p\u003e \u003c/div\u003e"},{"header":"5. Results","content":"\u003cdiv id=\"Sec22\" class=\"Section2\"\u003e \u003ch2\u003e5.1 Results of the Proposed System Design\u003c/h2\u003e \u003cp\u003eThe proposed duress-enabled banking system was evaluated conceptually using a prototype-based banking application aligned with the system architecture. Three scenarios were considered: (1) coercion/robbery, (2) fraudulent misuse by customers through forensic analysis, and (3) false positive entry of duress credentials through stress analysis. These scenarios reflect the most probable real-world contexts in which the duress function would be activated.\u003c/p\u003e \u003cp\u003eIn the robbery scenario, results indicate that when the duress PIN or login is entered, the attacker perceives the transaction as successful since they receive a normal confirmation alert. However, the funds remain within interbank transfer rails, making them traceable by the financial institution. Additionally, transaction restrictions such as a capped transfer limit and the absence of cash withdrawal options prevent large-scale loss. This outcome shows the effectiveness of the duress function in protecting customer assets under coercion while enabling authorities to track illicitly moved funds.\u003c/p\u003e \u003cp\u003eFor the fraud attempt scenario, where customers intentionally misuse the duress feature to scam merchants or evade payment, the fraud prevention module\u0026rsquo;s behavioral analytics, geolocation data, and biometric logs allow the bank to differentiate genuine duress cases from fraudulent claims. Expected results show that false duress claims can be reliably detected, thereby reducing the risk of abuse. However, the effectiveness of the system depends heavily on the complexity of the fraud detection algorithms and the availability of contextual data.\u003c/p\u003e \u003cp\u003eIn the false positive scenario, where a customer mistakenly enters a duress PIN, the system allows post-transaction verification. Users can confirm their identity through secondary authentication modes, such as voice recognition, OTP validation, or in-person verification. The outcome ensures that mistaken activations do not result in irreversible account restrictions. This flexibility strengthens user confidence in the system\u0026rsquo;s usability.\u003c/p\u003e \u003c/div\u003e \u003cdiv id=\"Sec23\" class=\"Section2\"\u003e \u003ch2\u003e5.2 System Implementation and User Interface\u003c/h2\u003e \u003cp\u003eThe implementation section demonstrates how the duress-enabled banking system operates through a series of user interface screens, starting with secure account registration and progressing through both normal and emergency (duress) operation modes. The registration interface enables users to input their personal details and create secure authentication credentials. The PIN configuration screen requires the creation of distinct normal and duress PINs, ensuring the system can differentiate between routine access and access triggered by coercion. Once authenticated with the normal PIN, users gain full access to the main dashboard, which provides a complete overview of account balances, recent transactions, and key banking services in a responsive and easy-to-use layout.\u003c/p\u003e \u003cp\u003eWhen the system is accessed through a duress PIN, it loads up the restricted dashboard designed to protect the user under threat by displaying only 10% of the actual balance and limiting transaction capabilities. Additional interfaces, such as the profile and forensic dashboard, summarize user activity, anomaly alerts, and logs for integrity checks, strengthening the system oversight and transparency. Stress-testing results further confirm system reliability, showing consistent anomaly detection across scenarios involving duress activity, high-value transactions, and irregular transaction patterns. These outcomes confirm the system\u0026rsquo;s ability to identify suspicious behavior and maintain security under various operational conditions.\u003c/p\u003e \u003c/div\u003e \u003cdiv id=\"Sec24\" class=\"Section2\"\u003e \u003ch2\u003e5.3 Comparative Evaluation\u003c/h2\u003e \u003cp\u003eWhen compared to traditional banking security features such as two-factor authentication (2FA), transaction alerts, and fraud monitoring systems, the proposed duress-enabled system offers a unique safety mechanism that directly addresses physical coercion, an area often neglected in digital banking security research (Sharma et al., 2024). While conventional methods secure transactions against cyber threats, they provide little to no protection when customers are under armed duress.\u003c/p\u003e \u003cp\u003eThe duress PIN system thus extends the security perimeter beyond digital threats to physical threat contexts. Moreover, unlike panic buttons or silent alerts used in ATM systems, the duress PIN operates seamlessly within existing mobile banking infrastructure, making it harder for attackers to detect its activation.\u003c/p\u003e \u003cp\u003eFigure\u0026nbsp;\u003cspan refid=\"Fig1\" class=\"InternalRef\"\u003e1\u003c/span\u003e\u003c/p\u003e \u003cp\u003e \u003c/p\u003e \u003cp\u003eComparison Chart for Novel Duress Study VS Previous Studies\u003c/p\u003e \u003cp\u003eThe comparative analysis reveals that the proposed Duress Framework addresses the protection against coercion, a critical gap in the existing literature. While previous studies by [\u003cspan citationid=\"CR1\" class=\"CitationRef\"\u003e1\u003c/span\u003e], [\u003cspan citationid=\"CR10\" class=\"CitationRef\"\u003e10\u003c/span\u003e], [\u003cspan citationid=\"CR3\" class=\"CitationRef\"\u003e3\u003c/span\u003e], and [\u003cspan citationid=\"CR14\" class=\"CitationRef\"\u003e14\u003c/span\u003e] have advanced blockchain logging, AI-based fraud detection, multi-factor authentication, and vulnerability identification, respectively, none of the studies provide protective measures against physical coercion. The chart, as seen in Fig.\u0026nbsp;3, visualizes capabilities across six different ways: coercion protection, authentication security, forensic logging, AI-based detection, real-time alert, and transaction control, which shows that the existing approaches fail when legitimate users are forced to authorize transactions under threat.\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\u003eComparison Table: Duress Banking Framework vs. Previous Studies\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\u003eStudy (Author, Year)\u003c/p\u003e \u003c/th\u003e \u003cth align=\"left\" colname=\"c2\"\u003e \u003cp\u003eFocus / Method\u003c/p\u003e \u003c/th\u003e \u003cth align=\"left\" colname=\"c3\"\u003e \u003cp\u003eLimitation\u003c/p\u003e \u003c/th\u003e \u003cth align=\"left\" colname=\"c4\"\u003e \u003cp\u003eGap Addressed by Duress Framework (2025)\u003c/p\u003e \u003c/th\u003e \u003c/tr\u003e \u003c/thead\u003e \u003ctbody\u003e \u003ctr\u003e \u003ctd align=\"left\" colname=\"c1\"\u003e \u003cp\u003e\u003cb\u003eKhan et al. (2023)\u003c/b\u003e [\u003cspan citationid=\"CR3\" class=\"CitationRef\"\u003e3\u003c/span\u003e]\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c2\"\u003e \u003cp\u003eMulti-factor authentication (MFA) and mobile financial authentication methods in Fintech\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c3\"\u003e \u003cp\u003eMFA is ineffective when the legitimate user is physically coerced into authorizing transactions; authentication factors assume user consent\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c4\"\u003e \u003cp\u003eIntroduces a covert duress PIN/login that signals a threat even during \"legitimate\" access while appearing normal to the coercer\u003c/p\u003e \u003c/td\u003e \u003c/tr\u003e \u003ctr\u003e \u003ctd align=\"left\" colname=\"c1\"\u003e \u003cp\u003e\u003cb\u003eIslam et al. (2023)\u003c/b\u003e [\u003cspan citationid=\"CR1\" class=\"CitationRef\"\u003e1\u003c/span\u003e]\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c2\"\u003e \u003cp\u003eBlockchain-based secure and tamper-proof forensic log data storage with strong access control\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c3\"\u003e \u003cp\u003eProvides integrity of logs but does not protect victims during real-time coercion scenarios; focuses on post-incident analysis only\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c4\"\u003e \u003cp\u003eAdds duress-triggered logging\u0026thinsp;+\u0026thinsp;quarantine routing\u0026thinsp;+\u0026thinsp;real-time protective measures for forced transfers during active coercion\u003c/p\u003e \u003c/td\u003e \u003c/tr\u003e \u003ctr\u003e \u003ctd align=\"left\" colname=\"c1\"\u003e \u003cp\u003e\u003cb\u003eSholapurapu (2023)\u003c/b\u003e [\u003cspan citationid=\"CR10\" class=\"CitationRef\"\u003e10\u003c/span\u003e]\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c2\"\u003e \u003cp\u003eAI-powered fraud detection for banking transactions using machine learning to identify suspicious patterns\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c3\"\u003e \u003cp\u003eFraud detection fails during coercion because the attacker uses normal credentials, and the behavior appears legitimate; it cannot distinguish forced vs. voluntary transactions\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c4\"\u003e \u003cp\u003eIntroduces coercion-sensitive transaction labeling independent of anomaly patterns; embeds forensic markers at the authentication level\u003c/p\u003e \u003c/td\u003e \u003c/tr\u003e \u003ctr\u003e \u003ctd align=\"left\" colname=\"c1\"\u003e \u003cp\u003e\u003cb\u003eSalami et al. (2025)\u003c/b\u003e [\u003cspan citationid=\"CR8\" class=\"CitationRef\"\u003e8\u003c/span\u003e]\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c2\"\u003e \u003cp\u003eAI-powered behavioral biometrics for next-generation fraud detection in digital banking\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c3\"\u003e \u003cp\u003eBiometric systems primarily prevent unauthorized access rather than identifying authorized users under external pressure\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c4\"\u003e \u003cp\u003eProvides a dual-authentication layer where biometrics verify identity while duress credentials activate protection protocols\u003c/p\u003e \u003c/td\u003e \u003c/tr\u003e \u003ctr\u003e \u003ctd align=\"left\" colname=\"c1\"\u003e \u003cp\u003e\u003cb\u003eImam et al. (2024)\u003c/b\u003e [\u003cspan citationid=\"CR14\" class=\"CitationRef\"\u003e14\u003c/span\u003e]\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c2\"\u003e \u003cp\u003eSecurity evaluation of mobile banking applications in Nigeria, identifying vulnerabilities (weak encryption, poor fraud controls)\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c3\"\u003e \u003cp\u003eIdentifies vulnerabilities but does not implement coercion-resistant defense mechanisms; descriptive analysis without a protective solution\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c4\"\u003e \u003cp\u003eImplements operational duress workflows, forced-transfer containment, and transaction restrictions specifically for high-risk environments\u003c/p\u003e \u003c/td\u003e \u003c/tr\u003e \u003ctr\u003e \u003ctd align=\"left\" colname=\"c1\"\u003e \u003cp\u003e\u003cb\u003eProposed Duress Banking Framework (2025)\u003c/b\u003e\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c2\"\u003e \u003cp\u003eCovert authentication\u0026thinsp;+\u0026thinsp;restricted transfers\u0026thinsp;+\u0026thinsp;immutable evidence logging\u0026thinsp;+\u0026thinsp;AI anomaly detection\u0026thinsp;+\u0026thinsp;recovery mechanisms\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c3\"\u003e \u003cp\u003e---\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c4\"\u003e \u003cp\u003eProvides comprehensive protection against coercion-driven transfers, combining detection, prevention, real-time safety measures, and post-incident recovery mechanisms\u003c/p\u003e \u003c/td\u003e \u003c/tr\u003e \u003c/tbody\u003e \u003c/colgroup\u003e \u003c/table\u003e\u003c/div\u003e \u003c/p\u003e \u003c/div\u003e"},{"header":"6 Discussion","content":"\u003cp\u003eThe results suggest that duress-enabled banking functions could significantly enhance the resilience of digital banking platforms in regions prone to armed robberies, kidnappings, and coercive crimes. In Nigeria, for instance, where mobile money adoption is rising but cash-related robberies remain prevalent, such systems could provide much-needed safety nets for users (Abood et al., 2022).\u003c/p\u003e \u003cp\u003eOne of the key insights from the simulated outcomes is the balance between security and usability. If duress transactions are too restrictive, attackers may become suspicious, endangering the user. Conversely, if they are too permissive, the system risks financial loss and fraud. The design of transaction ceilings and restricted functionality, therefore, represents a crucial trade-off that banks must calibrate carefully.\u003c/p\u003e \u003cp\u003eAnother important finding is the role of post-incident investigation. While the duress PIN protects the user during the attack, the effectiveness of recovery depends on the bank\u0026rsquo;s ability to track funds and verify claims. This underscores the importance of integrating AI-driven fraud detection and forensic auditing into the duress system.\u003c/p\u003e \u003cdiv id=\"Sec26\" class=\"Section2\"\u003e \u003ch2\u003e6.1 Implications for Banking Security\u003c/h2\u003e \u003cp\u003eThe proposed system has significant implications for both financial institutions and regulators. For banks, it represents a competitive advantage in enhancing customer trust and loyalty by prioritizing safety in situations where coercion is in play. For regulators, it highlights the need to develop legal frameworks that define liability, ensure data protection, and manage disputes arising from duress claims.\u003c/p\u003e \u003cp\u003eFurthermore, widespread adoption of duress-enabled banking could reshape criminal behavior. By reducing the utility of coercion-based theft since stolen funds remain traceable and partially restricted, such systems may deter attackers from targeting bank customers.\u003c/p\u003e \u003c/div\u003e \u003cdiv id=\"Sec27\" class=\"Section2\"\u003e \u003ch2\u003e6.2 User Interface Design and Implementation Insights\u003c/h2\u003e \u003cp\u003eThe practical implementation demonstrated in Section 4.10 reveals critical insights into balancing security functionality and user experience. The visual differentiation between normal and duress modes, particularly the restricted dashboard displaying only 10% of the actual balance, creates convincing deception for coercers while maintaining backend security protocols. The forensic dashboard integration provides security operations with comprehensive monitoring capabilities, though real-world effectiveness depends on user education and the ability to activate duress features reliably under actual coercion without arousing suspicion.\u003c/p\u003e \u003c/div\u003e \u003cdiv id=\"Sec28\" class=\"Section2\"\u003e \u003ch2\u003e6.3 Limitations of the Study\u003c/h2\u003e \u003cp\u003eDespite its potential, the proposed system has limitations. First, the results are based on conceptual simulations prototyped based on application tests for research purposes rather than live deployments for general use, meaning real-world performance could vary. Second, the system relies on interbank cooperation and strong digital infrastructures, which may not be uniformly available across developing regions. Third, attackers could adapt their tactics if they become aware of duress functions, potentially demanding higher amounts or multiple transactions.\u003c/p\u003e \u003c/div\u003e \u003cdiv id=\"Sec29\" class=\"Section2\"\u003e \u003ch2\u003e6.4 Future Work\u003c/h2\u003e \u003cp\u003eThe proposed duress banking authentication framework gives an opportunity for several future research directions. One promising avenue is enhanced multimodal duress signaling, combining subtle behavioral cues (e.g., typing pressure, gait recognition) with covert PIN modifications to improve detection reliability. Another area is blockchain-based immutable duress logging, ensuring tamper-proof evidence trails for law enforcement without compromising customer privacy.\u003c/p\u003e \u003cp\u003eFurthermore, AI-driven adaptive learning models could be trained continuously on evolving coercion patterns, reducing false positives while improving sensitivity to emerging threats. Integration with federated learning approaches may also ensure privacy-preserving model updates across financial institutions. On the policy side, collaboration with regulators and law enforcement is essential to establish legal and ethical frameworks that balance customer safety with due process.\u003c/p\u003e \u003cp\u003eFinally, field trials in controlled environments with banking partners would validate usability, scalability, and acceptance of duress systems in real-world scenarios, paving the way for enterprise adoption.\u003c/p\u003e \u003c/div\u003e"},{"header":"7. Conclusion","content":"\u003cp\u003eThis study has introduced a novel duress banking authentication system that integrates AI-driven anomaly detection, covert distress signaling, and blockchain-secured logging to enhance user safety in financial transactions. Distinct from other traditional banking security mechanisms that only guard against unauthorized access, this framework addresses threats based on coercion, thereby bridging a critical gap in financial cybersecurity. The contributions of this work include a hybrid security architecture combining traditional authentication with covert duress signaling. Comparative evaluation against traditional methods, highlighting advantages in resilience and trust, and a research framework aligning AI, anomaly detection, and secure SOC integration with regulatory considerations.\u003c/p\u003e \u003cp\u003eThrough transparency enhancement, compliance, and accessibility, this study shows how AI-driven duress authentication systems can redefine financial security, protect users under coercion, and foster safer digital banking ecosystems.\u003c/p\u003e"},{"header":"Abbreviations","content":"\u003cp\u003eAI\u0026nbsp; \u0026nbsp; \u0026nbsp; \u0026nbsp; \u0026nbsp; \u0026nbsp; \u0026nbsp; \u0026nbsp; \u0026nbsp; \u0026nbsp; \u0026nbsp; \u0026nbsp; \u0026nbsp; \u0026nbsp; \u0026nbsp; \u0026nbsp; \u0026nbsp; \u0026nbsp; \u0026nbsp; \u0026nbsp;Artificial Intelligence\u003c/p\u003e\n\u003cp\u003eAML\u0026nbsp; \u0026nbsp; \u0026nbsp; \u0026nbsp; \u0026nbsp; \u0026nbsp; \u0026nbsp; \u0026nbsp; \u0026nbsp; \u0026nbsp; \u0026nbsp; \u0026nbsp; \u0026nbsp; \u0026nbsp; \u0026nbsp; \u0026nbsp; \u0026nbsp;\u0026nbsp;Anti-Money Laundering\u003c/p\u003e\n\u003cp\u003eAPI\u0026nbsp; \u0026nbsp; \u0026nbsp; \u0026nbsp; \u0026nbsp; \u0026nbsp; \u0026nbsp; \u0026nbsp; \u0026nbsp; \u0026nbsp; \u0026nbsp; \u0026nbsp; \u0026nbsp; \u0026nbsp; \u0026nbsp; \u0026nbsp; \u0026nbsp; \u0026nbsp; \u0026nbsp;Application Programming Interface\u003c/p\u003e\n\u003cp\u003eATM\u0026nbsp; \u0026nbsp; \u0026nbsp; \u0026nbsp; \u0026nbsp; \u0026nbsp; \u0026nbsp; \u0026nbsp; \u0026nbsp; \u0026nbsp; \u0026nbsp; \u0026nbsp; \u0026nbsp; \u0026nbsp; \u0026nbsp; \u0026nbsp; \u0026nbsp; \u0026nbsp;Automated Teller Machine\u003c/p\u003e\n\u003cp\u003eCBN\u0026nbsp; \u0026nbsp; \u0026nbsp; \u0026nbsp; \u0026nbsp; \u0026nbsp; \u0026nbsp; \u0026nbsp; \u0026nbsp; \u0026nbsp; \u0026nbsp; \u0026nbsp; \u0026nbsp; \u0026nbsp; \u0026nbsp; \u0026nbsp; \u0026nbsp; \u0026nbsp;Central Bank of Nigeria\u003c/p\u003e\n\u003cp\u003eDSRM\u0026nbsp; \u0026nbsp; \u0026nbsp; \u0026nbsp; \u0026nbsp; \u0026nbsp; \u0026nbsp; \u0026nbsp; \u0026nbsp; \u0026nbsp; \u0026nbsp; \u0026nbsp; \u0026nbsp; \u0026nbsp; \u0026nbsp; \u0026nbsp;\u0026nbsp;Design Science Research Methodology\u003c/p\u003e\n\u003cp\u003eE2EE\u0026nbsp; \u0026nbsp; \u0026nbsp; \u0026nbsp; \u0026nbsp; \u0026nbsp; \u0026nbsp; \u0026nbsp; \u0026nbsp; \u0026nbsp; \u0026nbsp; \u0026nbsp; \u0026nbsp; \u0026nbsp; \u0026nbsp; \u0026nbsp; \u0026nbsp;\u0026nbsp;End-to-End Encryption\u003c/p\u003e\n\u003cp\u003eGDPR\u0026nbsp; \u0026nbsp; \u0026nbsp; \u0026nbsp; \u0026nbsp; \u0026nbsp; \u0026nbsp; \u0026nbsp; \u0026nbsp; \u0026nbsp; \u0026nbsp; \u0026nbsp; \u0026nbsp; \u0026nbsp; \u0026nbsp; \u0026nbsp; \u0026nbsp;General Data Protection Regulation\u003c/p\u003e\n\u003cp\u003eGPS\u0026nbsp; \u0026nbsp; \u0026nbsp; \u0026nbsp; \u0026nbsp; \u0026nbsp; \u0026nbsp; \u0026nbsp; \u0026nbsp; \u0026nbsp; \u0026nbsp; \u0026nbsp; \u0026nbsp; \u0026nbsp; \u0026nbsp; \u0026nbsp; \u0026nbsp; \u0026nbsp;\u0026nbsp;Global Positioning System\u003c/p\u003e\n\u003cp\u003eIoT\u0026nbsp; \u0026nbsp; \u0026nbsp; \u0026nbsp; \u0026nbsp; \u0026nbsp; \u0026nbsp; \u0026nbsp; \u0026nbsp; \u0026nbsp; \u0026nbsp; \u0026nbsp; \u0026nbsp; \u0026nbsp; \u0026nbsp; \u0026nbsp; \u0026nbsp; \u0026nbsp; \u0026nbsp;Internet of Things\u003c/p\u003e\n\u003cp\u003eISO\u0026nbsp; \u0026nbsp; \u0026nbsp; \u0026nbsp; \u0026nbsp; \u0026nbsp; \u0026nbsp; \u0026nbsp; \u0026nbsp; \u0026nbsp; \u0026nbsp; \u0026nbsp; \u0026nbsp; \u0026nbsp; \u0026nbsp; \u0026nbsp; \u0026nbsp; \u0026nbsp; \u0026nbsp;International Organization for Standardization\u003c/p\u003e\n\u003cp\u003eKYC\u0026nbsp; \u0026nbsp; \u0026nbsp; \u0026nbsp; \u0026nbsp; \u0026nbsp; \u0026nbsp; \u0026nbsp; \u0026nbsp; \u0026nbsp; \u0026nbsp; \u0026nbsp; \u0026nbsp; \u0026nbsp; \u0026nbsp; \u0026nbsp; \u0026nbsp; \u0026nbsp;Know Your Customer\u003c/p\u003e\n\u003cp\u003eMFA\u0026nbsp; \u0026nbsp; \u0026nbsp; \u0026nbsp; \u0026nbsp; \u0026nbsp; \u0026nbsp; \u0026nbsp; \u0026nbsp; \u0026nbsp; \u0026nbsp; \u0026nbsp; \u0026nbsp; \u0026nbsp; \u0026nbsp; \u0026nbsp; \u0026nbsp; \u0026nbsp;Multi-Factor Authentication\u003c/p\u003e\n\u003cp\u003eML\u0026nbsp; \u0026nbsp; \u0026nbsp; \u0026nbsp; \u0026nbsp; \u0026nbsp; \u0026nbsp; \u0026nbsp; \u0026nbsp; \u0026nbsp; \u0026nbsp; \u0026nbsp; \u0026nbsp; \u0026nbsp; \u0026nbsp; \u0026nbsp; \u0026nbsp; \u0026nbsp; \u0026nbsp;Machine Learning\u003c/p\u003e\n\u003cp\u003eOTP\u0026nbsp; \u0026nbsp; \u0026nbsp; \u0026nbsp; \u0026nbsp; \u0026nbsp; \u0026nbsp; \u0026nbsp; \u0026nbsp; \u0026nbsp; \u0026nbsp; \u0026nbsp; \u0026nbsp; \u0026nbsp; \u0026nbsp; \u0026nbsp; \u0026nbsp; \u0026nbsp;\u0026nbsp;One-Time Password\u003c/p\u003e\n\u003cp\u003ePIN\u0026nbsp; \u0026nbsp; \u0026nbsp; \u0026nbsp; \u0026nbsp; \u0026nbsp; \u0026nbsp; \u0026nbsp; \u0026nbsp; \u0026nbsp; \u0026nbsp; \u0026nbsp; \u0026nbsp; \u0026nbsp; \u0026nbsp; \u0026nbsp; \u0026nbsp; \u0026nbsp; \u0026nbsp;Personal Identification Number\u003c/p\u003e\n\u003cp\u003eSIEM\u0026nbsp; \u0026nbsp; \u0026nbsp; \u0026nbsp; \u0026nbsp; \u0026nbsp; \u0026nbsp; \u0026nbsp; \u0026nbsp; \u0026nbsp; \u0026nbsp; \u0026nbsp; \u0026nbsp; \u0026nbsp; \u0026nbsp; \u0026nbsp; \u0026nbsp;\u0026nbsp;Security Information and Event Management\u003c/p\u003e\n\u003cp\u003eSOC\u0026nbsp; \u0026nbsp; \u0026nbsp; \u0026nbsp; \u0026nbsp; \u0026nbsp; \u0026nbsp; \u0026nbsp; \u0026nbsp; \u0026nbsp; \u0026nbsp; \u0026nbsp; \u0026nbsp; \u0026nbsp; \u0026nbsp; \u0026nbsp; \u0026nbsp; \u0026nbsp;\u0026nbsp;Security Operations Center\u003c/p\u003e\n\u003cp\u003eSOP\u0026nbsp; \u0026nbsp; \u0026nbsp; \u0026nbsp; \u0026nbsp; \u0026nbsp; \u0026nbsp; \u0026nbsp; \u0026nbsp; \u0026nbsp; \u0026nbsp; \u0026nbsp; \u0026nbsp; \u0026nbsp; \u0026nbsp; \u0026nbsp; \u0026nbsp; \u0026nbsp;\u0026nbsp;Standard Operating Procedure\u003c/p\u003e\n\u003cp\u003eUI\u0026nbsp; \u0026nbsp; \u0026nbsp; \u0026nbsp; \u0026nbsp; \u0026nbsp; \u0026nbsp; \u0026nbsp; \u0026nbsp; \u0026nbsp; \u0026nbsp; \u0026nbsp; \u0026nbsp; \u0026nbsp; \u0026nbsp; \u0026nbsp; \u0026nbsp; \u0026nbsp; \u0026nbsp; \u0026nbsp;User Interface\u003c/p\u003e\n\u003cp\u003eXAI \u0026nbsp; \u0026nbsp; \u0026nbsp; \u0026nbsp; \u0026nbsp; \u0026nbsp; \u0026nbsp; \u0026nbsp; \u0026nbsp; \u0026nbsp; \u0026nbsp; \u0026nbsp; \u0026nbsp; \u0026nbsp; \u0026nbsp; \u0026nbsp; \u0026nbsp; \u0026nbsp;Explainable Artificial Intelligence\u003c/p\u003e"},{"header":"Declarations","content":"\u003cp\u003e\u003cstrong\u003eFunding\u003c/strong\u003e\u003c/p\u003e\n\u003cp\u003eNo funding was received\u003c/p\u003e\n\u003cp\u003e\u003cstrong\u003eAuthor information\u003c/strong\u003e\u003c/p\u003e\n\u003cp\u003e\u003cstrong\u003eAuthors and Affiliations\u003c/strong\u003e\u003c/p\u003e\n\u003cp\u003eIdris Olanrewaju Ibraheem, Al-Hikmah University\u003c/p\u003e\n\u003cp\u003e\u003cstrong\u003eContributions\u003c/strong\u003e\u003c/p\u003e\n\u003cp\u003eIdris Ibraheem conceptualized the study and designed the methodology. Muhammad Tijani and Idris Ibraheem supervised the research process. Ibraheem developed the codes and conducted technical validations. Tijani and Ibraheem provided critical insights into the analysis of the results. All the authors reviewed and approved the final manuscript.\u003c/p\u003e\n\u003cp\u003e\u003cstrong\u003eCorresponding author\u003c/strong\u003e\u003c/p\u003e\n\u003cp\u003eIdris Olanrewaju Ibraheem\u003c/p\u003e\n\u003cp\u003e\u003cstrong\u003eEthics declarations\u003c/strong\u003e\u003c/p\u003e\n\u003cp\u003e\u003cstrong\u003eConflict of interest\u003c/strong\u003e\u003c/p\u003e\n\u003cp\u003eThere is no conflicting interest\u003c/p\u003e\n\u003cp\u003e\u003cstrong\u003eEthical approval\u003c/strong\u003e\u003c/p\u003e\n\u003cp\u003eNot applicable\u003c/p\u003e"},{"header":"References","content":"\u003col\u003e\u003cli\u003e\u003cspan\u003eIslam ME, Islam MR, Chetty M, Lim S, Chadhar M. User authentication and access control to blockchain-based forensic log data. EURASIP J Inform Secur. 2023;2023(1):7. \u003cspan class=\"ExternalRef\"\u003e\u003cspan class=\"RefSource\"\u003ehttps://doi.org/10.1186/s13635-023-00142-3\u003c/span\u003e\u003cspan address=\"10.1186/s13635-023-00142-3\" targettype=\"DOI\" class=\"RefTarget\"\u003e\u003c/span\u003e\u003c/span\u003e.\u003c/span\u003e\u003c/li\u003e \u003cli\u003e\u003cspan\u003eLi W, Feng Y, Liu N, Li Y, Fu X, Yu Y. A secure and efficient log storage and query framework based on blockchain. Comput Netw. 2024;252:110683. \u003cspan class=\"ExternalRef\"\u003e\u003cspan class=\"RefSource\"\u003ehttps://doi.org/10.1016/j.comnet.2024.110683\u003c/span\u003e\u003cspan address=\"10.1016/j.comnet.2024.110683\" targettype=\"DOI\" class=\"RefTarget\"\u003e\u003c/span\u003e\u003c/span\u003e.\u003c/span\u003e\u003c/li\u003e \u003cli\u003e\u003cspan\u003eKhan A, Zhu Y, Raza A. Role of authentication factors in Fin-tech mobile transaction security. J Big Data. 2023;10(1):1\u0026ndash;20. \u003cspan class=\"ExternalRef\"\u003e\u003cspan class=\"RefSource\"\u003ehttps://doi.org/10.1186/s40537-023-00807-3\u003c/span\u003e\u003cspan address=\"10.1186/s40537-023-00807-3\" targettype=\"DOI\" class=\"RefTarget\"\u003e\u003c/span\u003e\u003c/span\u003e.\u003c/span\u003e\u003c/li\u003e \u003cli\u003e\u003cspan\u003eNanda A, Jeong JJ, Shah SWA, Nosouhi M, Doss R. Examining usable security features and user perceptions of Physical Authentication Devices. Computers Secur. 2024;139:103664. \u003cspan class=\"ExternalRef\"\u003e\u003cspan class=\"RefSource\"\u003ehttps://doi.org/10.1016/j.cose.2023.103664\u003c/span\u003e\u003cspan address=\"10.1016/j.cose.2023.103664\" targettype=\"DOI\" class=\"RefTarget\"\u003e\u003c/span\u003e\u003c/span\u003e.\u003c/span\u003e\u003c/li\u003e \u003cli\u003e\u003cspan\u003eYang L, Qin S. Identify user features impacting keystroke, mouse and touchscreen dynamics. Multimedia Tools Appl. 2025;1\u0026ndash;29. \u003cspan class=\"ExternalRef\"\u003e\u003cspan class=\"RefSource\"\u003ehttps://doi.org/10.1007/s11042-025-21043-2\u003c/span\u003e\u003cspan address=\"10.1007/s11042-025-21043-2\" targettype=\"DOI\" class=\"RefTarget\"\u003e\u003c/span\u003e\u003c/span\u003e.\u003c/span\u003e\u003c/li\u003e \u003cli\u003e\u003cspan\u003eMowbray F, Mills F, Symons C, Aml\u0026ocirc;t R, Rubin G. A systematic review of the use of mobile alerting to inform the public about emergencies and the factors that influence the public response. J Contingencies Crisis Manag. 2024;32(1):e12499. \u003cspan class=\"ExternalRef\"\u003e\u003cspan class=\"RefSource\"\u003ehttps://doi.org/10.1111/1468-5973.12499\u003c/span\u003e\u003cspan address=\"10.1111/1468-5973.12499\" targettype=\"DOI\" class=\"RefTarget\"\u003e\u003c/span\u003e\u003c/span\u003e.\u003c/span\u003e\u003c/li\u003e \u003cli\u003e\u003cspan\u003eOyekunle SM, Popoola AD, Kolo FHO, Ogunmolu AM, Adesokan-Imran TO. Intelligent fraud prevention information banking: A data governancecentric approach using behavioural biometrics. Asian J Res Comput Sci. 2025;18(5):525\u0026ndash;43. \u003cspan class=\"ExternalRef\"\u003e\u003cspan class=\"RefSource\"\u003ehttps://doi.org/10.9734/ajrcos/2025/v18i5672\u003c/span\u003e\u003cspan address=\"10.9734/ajrcos/2025/v18i5672\" targettype=\"DOI\" class=\"RefTarget\"\u003e\u003c/span\u003e\u003c/span\u003e.\u003c/span\u003e\u003c/li\u003e \u003cli\u003e\u003cspan\u003eSalami IA, Popoola AD, Gbadebo MO, Kolo FHO, Adesokan-Imran TO. AI-powered behavioural biometrics for fraud detection in digital banking: A next-generation approach to financial cybersecurity. Asian J Res Comput Sci. 2025;18(4):473\u0026ndash;94. \u003cspan class=\"ExternalRef\"\u003e\u003cspan class=\"RefSource\"\u003ehttps://doi.org/10.9734/ajrcos/2025/v18i4632\u003c/span\u003e\u003cspan address=\"10.9734/ajrcos/2025/v18i4632\" targettype=\"DOI\" class=\"RefTarget\"\u003e\u003c/span\u003e\u003c/span\u003e.\u003c/span\u003e\u003c/li\u003e \u003cli\u003e\u003cspan\u003eBanga L, Pillai S. (2021). \u003cem\u003eImpact of Behavioural Biometrics on Mobile Banking System\u003c/em\u003e. Journal of Physics: Conference Series, 1964(6). \u003cspan class=\"ExternalRef\"\u003e\u003cspan class=\"RefSource\"\u003ehttps://doi.org/10.1088/1742-6596/1964/6/062109\u003c/span\u003e\u003cspan address=\"10.1088/1742-6596/1964/6/062109\" targettype=\"DOI\" class=\"RefTarget\"\u003e\u003c/span\u003e\u003c/span\u003e\u003c/span\u003e\u003c/li\u003e \u003cli\u003e\u003cspan\u003eSholapurapu PK. (2023). AI-Powered Banking in Revolutionizing Fraud Detection: Enhancing Machine Learning to Secure Financial Transactions. South East Eur J Public Health, \u003cem\u003e20\u003c/em\u003e.\u003c/span\u003e\u003c/li\u003e \u003cli\u003e\u003cspan\u003eRaghu N, Kannanugo N, Trupti VN, Ojashwini RN, Kiran B, Deepthi M. Real-time fraud detection in crypto-currencies: Leveraging AI and blockchain. Applications of Blockchain and Artificial Intelligence in Finance and Governance. CRC; 2024. pp. 28\u0026ndash;66.\u003c/span\u003e\u003c/li\u003e \u003cli\u003e\u003cspan\u003ePutrevu J, Mertzanis C. The adoption of digital payments in emerging economies: challenges and policy responses. Digit Policy Regul Gov. 2024;26(5):476\u0026ndash;500. \u003cspan class=\"ExternalRef\"\u003e\u003cspan class=\"RefSource\"\u003ehttps://doi.org/10.1108/DPRG-06-2023-0077\u003c/span\u003e\u003cspan address=\"10.1108/DPRG-06-2023-0077\" targettype=\"DOI\" class=\"RefTarget\"\u003e\u003c/span\u003e\u003c/span\u003e.\u003c/span\u003e\u003c/li\u003e \u003cli\u003e\u003cspan\u003eJabez J, Muthukumar BJPCS. Intrusion Detection System (IDS): Anomaly detection using outlier detection approach. Procedia Comput Sci. 2015;48:338\u0026ndash;46. \u003cspan class=\"ExternalRef\"\u003e\u003cspan class=\"RefSource\"\u003ehttps://doi.org/10.1016/j.procs.2015.04.191\u003c/span\u003e\u003cspan address=\"10.1016/j.procs.2015.04.191\" targettype=\"DOI\" class=\"RefTarget\"\u003e\u003c/span\u003e\u003c/span\u003e.\u003c/span\u003e\u003c/li\u003e \u003cli\u003e\u003cspan\u003eImam AY, Usman HI, Abba A. Security analysis and evaluation of mobile banking applications in Nigeria. Int J Inf Commun Technol ISSN. 2024;2252(8776):8776. \u003cspan class=\"ExternalRef\"\u003e\u003cspan class=\"RefSource\"\u003ehttp://doi.org/10.11591/ijict.v13i3.pp354-361\u003c/span\u003e\u003cspan address=\"10.11591/ijict.v13i3.pp354-361\" targettype=\"DOI\" class=\"RefTarget\"\u003e\u003c/span\u003e\u003c/span\u003e.\u003c/span\u003e\u003c/li\u003e \u003cli\u003e\u003cspan\u003eVanini P, Rossi S, Zvizdic E, Domenig T. Online payment fraud: from anomaly detection to risk management. Financial Innov. 2023;9(1):66. \u003cspan class=\"ExternalRef\"\u003e\u003cspan class=\"RefSource\"\u003e10.1186/s40854-023-00470-w\u003c/span\u003e\u003cspan address=\"10.1186/s40854-023-00470-w\" targettype=\"DOI\" class=\"RefTarget\"\u003e\u003c/span\u003e\u003c/span\u003e.\u003c/span\u003e\u003c/li\u003e \u003cli\u003e\u003cspan\u003eKaur S, Arora A, Goyal AK. A Bibliometric Review on the Evolution of Technology in Sustainability Reporting: With Reference to Artificial Intelligence. Sustain Report Blockchain Technol. 2024;54\u0026ndash;70. \u003cspan class=\"ExternalRef\"\u003e\u003cspan class=\"RefSource\"\u003e10.4324/9781003378341-6\u003c/span\u003e\u003cspan address=\"10.4324/9781003378341-6\" targettype=\"DOI\" class=\"RefTarget\"\u003e\u003c/span\u003e\u003c/span\u003e.\u003c/span\u003e\u003c/li\u003e \u003cli\u003e\u003cspan\u003eJavaheri D, Fahmideh M, Chizari H, Lalbakhsh P, Hur J. Cybersecurity threats in FinTech: A systematic review. Expert Syst Appl. 2024;241:122697. \u003cspan class=\"ExternalRef\"\u003e\u003cspan class=\"RefSource\"\u003ehttps://doi.org/10.1016/j.eswa.2023.122697\u003c/span\u003e\u003cspan address=\"10.1016/j.eswa.2023.122697\" targettype=\"DOI\" class=\"RefTarget\"\u003e\u003c/span\u003e\u003c/span\u003e.\u003c/span\u003e\u003c/li\u003e \u003cli\u003e\u003cspan\u003eHussain S, Gupta S, Bhardwaj S. Determinants inhibiting digital payment system adoption: an Indian perspective. Qualitative Res Financial Markets. 2025;17(4):716\u0026ndash;48. \u003cspan class=\"ExternalRef\"\u003e\u003cspan class=\"RefSource\"\u003ehttps://doi.org/10.1108/QRFM-09-2023-0223\u003c/span\u003e\u003cspan address=\"10.1108/QRFM-09-2023-0223\" targettype=\"DOI\" class=\"RefTarget\"\u003e\u003c/span\u003e\u003c/span\u003e.\u003c/span\u003e\u003c/li\u003e \u003cli\u003e\u003cspan\u003eSneha A, Patil H. MOBILE BANKING AS AN EMERGING TREND IN COMMERCE. Int J Res -GRANTHAALAYAH. 2025;13(5):7\u0026ndash;21. \u003cspan class=\"ExternalRef\"\u003e\u003cspan class=\"RefSource\"\u003ehttps://doi.org/10.29121/granthaalayah.v13.i5.2025.6151\u003c/span\u003e\u003cspan address=\"10.29121/granthaalayah.v13.i5.2025.6151\" targettype=\"DOI\" class=\"RefTarget\"\u003e\u003c/span\u003e\u003c/span\u003e.\u003c/span\u003e\u003c/li\u003e \u003cli\u003e\u003cspan\u003eFolami RA, Yinusa GO, Toriola AK. Digital payment fraud and bank fragility: Evidence from deposit money banks in Nigeria. Afr J Economic Rev. 2024;12(4). \u003cspan class=\"ExternalRef\"\u003e\u003cspan class=\"RefSource\"\u003ehttps://doi.org/10.22004/ag.econ.362925\u003c/span\u003e\u003cspan address=\"10.22004/ag.econ.362925\" targettype=\"DOI\" class=\"RefTarget\"\u003e\u003c/span\u003e\u003c/span\u003e.\u003c/span\u003e\u003c/li\u003e \u003cli\u003e\u003cspan\u003eHa D, Le P, Nguyen DK. Financial inclusion and fintech: a state-of-the-art systematic literature review. Financ Innov. 2025;11:69. \u003cspan class=\"ExternalRef\"\u003e\u003cspan class=\"RefSource\"\u003ehttps://doi.org/10.1186/s40854-024-00741-0\u003c/span\u003e\u003cspan address=\"10.1186/s40854-024-00741-0\" targettype=\"DOI\" class=\"RefTarget\"\u003e\u003c/span\u003e\u003c/span\u003e.\u003c/span\u003e\u003c/li\u003e \u003cli\u003e\u003cspan\u003eHu B, Zhu L, Dong Q, Qian K, Cai H, Tian F. Physiological electrosignal asynchronous acquisition technology: Insight and perspectives. IEEE Trans Comput Social Syst. 2024;11(1):5\u0026ndash;24. \u003cspan class=\"ExternalRef\"\u003e\u003cspan class=\"RefSource\"\u003ehttps://doi.org/10.1109/TCSS.2024.3350958\u003c/span\u003e\u003cspan address=\"10.1109/TCSS.2024.3350958\" targettype=\"DOI\" class=\"RefTarget\"\u003e\u003c/span\u003e\u003c/span\u003e.\u003c/span\u003e\u003c/li\u003e \u003cli\u003e\u003cspan\u003eBeiying L, Bin Z. (2025). Detecting Psychological Stress in Online Learning Environments via Secure Multimodal Behavioral Analysis. ICCSIE '25: Proceedings of the 10th International Conference on Cyber Security and Information Engineering \u003cspan class=\"ExternalRef\"\u003e\u003cspan class=\"RefSource\"\u003ehttps://doi.org/10.1145/3759179.3760449\u003c/span\u003e\u003cspan address=\"10.1145/3759179.3760449\" targettype=\"DOI\" class=\"RefTarget\"\u003e\u003c/span\u003e\u003c/span\u003e\u003c/span\u003e\u003c/li\u003e \u003cli\u003e\u003cspan\u003eMalady L. Consumer protection issues for digital financial services in emerging markets. Bank Finance Law Rev. 2016;31(2):389\u0026ndash;401. \u003cspan class=\"ExternalRef\"\u003e\u003cspan class=\"RefSource\"\u003ehttps://doi.org/10.2139/ssrn.3028371\u003c/span\u003e\u003cspan address=\"10.2139/ssrn.3028371\" targettype=\"DOI\" class=\"RefTarget\"\u003e\u003c/span\u003e\u003c/span\u003e.\u003c/span\u003e\u003c/li\u003e \u003cli\u003e\u003cspan\u003eMill ER, Garn W, Ryman-Tubb NF, Turner C. Opportunities in real time fraud detection: an explainable artificial intelligence (XAI) research agenda. Int J Adv Comput Sci Appl. 2023;14(5):1172\u0026ndash;86. \u003cspan class=\"ExternalRef\"\u003e\u003cspan class=\"RefSource\"\u003ehttps://doi.org/10.14569/IJACSA.2023.01405121\u003c/span\u003e\u003cspan address=\"10.14569/IJACSA.2023.01405121\" targettype=\"DOI\" class=\"RefTarget\"\u003e\u003c/span\u003e\u003c/span\u003e.\u003c/span\u003e\u003c/li\u003e \u003cli\u003e\u003cspan\u003eJindal P, Chavan L. (2023). Role of blockchain technology in creating blue ocean strategy for banking products and services. In \u003cem\u003eContemporary studies of risks in emerging technology, part B\u003c/em\u003e (pp. 169\u0026ndash;182). Emerald Publishing Limited. \u003cspan class=\"ExternalRef\"\u003e\u003cspan class=\"RefSource\"\u003ehttps://doi.org/10.1108/978-1-80455-566-820231008\u003c/span\u003e\u003cspan address=\"10.1108/978-1-80455-566-820231008\" targettype=\"DOI\" class=\"RefTarget\"\u003e\u003c/span\u003e\u003c/span\u003e\u003c/span\u003e\u003c/li\u003e \u003cli\u003e\u003cspan\u003eZhang Y, Zheng XT, Zhang X, Pan J, Thean AVY. Hybrid integration of wearable devices for physiological monitoring. Chem Rev. 2024;124(18):10386\u0026ndash;434. \u003cspan class=\"ExternalRef\"\u003e\u003cspan class=\"RefSource\"\u003ehttps://doi.org/10.1021/acs.chemrev.3c00471\u003c/span\u003e\u003cspan address=\"10.1021/acs.chemrev.3c00471\" targettype=\"DOI\" class=\"RefTarget\"\u003e\u003c/span\u003e\u003c/span\u003e.\u003c/span\u003e\u003c/li\u003e \u003cli\u003e\u003cspan\u003eRathore SS, Dewangan NK, Potdar RM, Barde P, Jumle P. (2024). IoT-Based Smart Safety Analyzer for Women. In \u003cem\u003eImpact of AI on Advancing Women's Safety\u003c/em\u003e (pp. 185\u0026ndash;199). IGI Global Scientific Publishing. \u003cspan class=\"ExternalRef\"\u003e\u003cspan class=\"RefSource\"\u003e10.4018/979-8-3693-2679-4.ch012\u003c/span\u003e\u003cspan address=\"10.4018/979-8-3693-2679-4.ch012\" targettype=\"DOI\" class=\"RefTarget\"\u003e\u003c/span\u003e\u003c/span\u003e\u003c/span\u003e\u003c/li\u003e \u003cli\u003e\u003cspan\u003eBharathi PS, Judgi T, Pradeep D, Samhan TSA, A. A. A., Giri J. (2025). A Novel Internet Of Things (IoT) Enabled Women Safety System Design with Emergency Alert Mechanism. In \u003cem\u003e2025 International Conference on Frontier Technologies and Solutions (ICFTS)\u003c/em\u003e (pp. 1\u0026ndash;7). IEEE. \u003cspan class=\"ExternalRef\"\u003e\u003cspan class=\"RefSource\"\u003ehttps://doi.org/10.1109/ICFTS62006.2025.11031774\u003c/span\u003e\u003cspan address=\"10.1109/ICFTS62006.2025.11031774\" targettype=\"DOI\" class=\"RefTarget\"\u003e\u003c/span\u003e\u003c/span\u003e\u003c/span\u003e\u003c/li\u003e \u003cli\u003e\u003cspan\u003ePatil D. (2024). Explainable Artificial Intelligence (XAI) for industry applications: Enhancing transparency, trust, and informed decision-making in business operation. \u003cem\u003eTrust, And Informed Decision-Making In Business Operation (December 03, 2024)\u003c/em\u003e. \u003cspan class=\"ExternalRef\"\u003e\u003cspan class=\"RefSource\"\u003ehttps://ssrn.com/abstract=5057402\u003c/span\u003e\u003cspan address=\"https://ssrn.com/abstract=5057402\" targettype=\"URL\" class=\"RefTarget\"\u003e\u003c/span\u003e\u003c/span\u003e\u003c/span\u003e\u003c/li\u003e \u003cli\u003e\u003cspan\u003eSivaranjani S. Transforming Fraud Detection in Banking with Explainable AI: Enhancing Transparency and Trust. J Technol Inf Eng. 2025;4(2):251\u0026ndash;60. \u003cspan class=\"ExternalRef\"\u003e\u003cspan class=\"RefSource\"\u003ehttps://doi.org/10.51903/jtie.v4i2.267\u003c/span\u003e\u003cspan address=\"10.51903/jtie.v4i2.267\" targettype=\"DOI\" class=\"RefTarget\"\u003e\u003c/span\u003e\u003c/span\u003e.\u003c/span\u003e\u003c/li\u003e \u003cli\u003e\u003cspan\u003eSalami IA, Popoola AD, Gbadebo MO, Kolo FHO, Adesokan-Imran TO. AI-Powered Behavioural Biometrics for Fraud Detection in Digital Banking: A Next-Generation Approach to Financial Cybersecurity. Asian J Res Comput Sci. 2025;18(4):473\u0026ndash;94. \u003cspan class=\"ExternalRef\"\u003e\u003cspan class=\"RefSource\"\u003ehttps://doi.org/10.9734/ajrcos/2025/v18i4632\u003c/span\u003e\u003cspan address=\"10.9734/ajrcos/2025/v18i4632\" targettype=\"DOI\" class=\"RefTarget\"\u003e\u003c/span\u003e\u003c/span\u003e.\u003c/span\u003e\u003c/li\u003e \u003cli\u003e\u003cspan\u003eChoudhary P. Data privacy and security in the banking sector: challenges and best practices. Issue 4 Int'l JL Mgmt Hum. 2023;6:1635. \u003cspan class=\"ExternalRef\"\u003e\u003cspan class=\"RefSource\"\u003ehttps://doij.org/10.10000/IJLMH.115613\u003c/span\u003e\u003cspan address=\"https://doij.10.10000/IJLMH.115613\" targettype=\"DOI\" class=\"RefTarget\"\u003e\u003c/span\u003e\u003c/span\u003e.\u003c/span\u003e\u003c/li\u003e \u003cli\u003e\u003cspan\u003eBuccafurri F, De Angelis V, Lazzaro S. A blockchain-based framework to enhance anonymous services with accountability guarantees. Future Internet. 2022;14(8):243. \u003cspan class=\"ExternalRef\"\u003e\u003cspan class=\"RefSource\"\u003ehttps://doi.org/10.3390/fi14080243\u003c/span\u003e\u003cspan address=\"10.3390/fi14080243\" targettype=\"DOI\" class=\"RefTarget\"\u003e\u003c/span\u003e\u003c/span\u003e.\u003c/span\u003e\u003c/li\u003e\u003c/ol\u003e"}],"fulltextSource":"","fullText":"","funders":[],"hasAdminPriorityOnWorkflow":false,"hasManuscriptDocX":true,"hasOptedInToPreprint":true,"hasPassedJournalQc":"","hasAnyPriority":false,"hideJournal":false,"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":"humancentric-intelligent-systems","isNatureJournal":false,"hasQc":true,"allowDirectSubmit":false,"externalIdentity":"","sideBox":"Learn more about [Human-Centric Intelligent Systems](https://link.springer.com/journal/44230)","snPcode":"44230","submissionUrl":"https://submission.springernature.com/new-submission/44230/3","title":"Human-Centric Intelligent Systems","twitterHandle":"","acdcEnabled":true,"dfaEnabled":true,"editorialSystem":"stoa","reportingPortfolio":"Springer Open","inReviewEnabled":true,"inReviewRevisionsEnabled":true},"keywords":"Duress-enabled banking, Coercion, Authentication, Mobile banking security, Fintech, Forensic logging, Financial cybersecurity","lastPublishedDoi":"10.21203/rs.3.rs-8279747/v1","lastPublishedDoiUrl":"https://doi.org/10.21203/rs.3.rs-8279747/v1","license":{"name":"CC BY 4.0","url":"https://creativecommons.org/licenses/by/4.0/"},"manuscriptAbstract":"\u003cp\u003eThis study addresses the critical security gap in mobile banking systems where victims of physical coercion are forced to authorize financial transactions under threat. A novel duress-enabled banking framework was designed and implemented, incorporating dual-authentication mechanisms, duress PINs, and duress login modes that enable victims to comply with attackers while covertly activating protective measures. The system combines AI-driven anomaly detection, behavioral biometrics, and blockchain-inspired fixed logging through a comprehensive, coercion-resistant architecture. When duress credentials are entered, transactions appear normal to the coercers but trigger backend restrictions that limit transfer amounts, disable cash withdrawals, route funds through traceable interbank channels, embed forensic markers, and issue silent alerts to bank security operations. A prototype was developed and evaluated through scenario-based activities covering robbery situations, potential misuse, and accidental activation. The results show an effective balance between the safety of the victim, recovery of funds, and abuse prevention. The framework uses machine learning algorithms, verification of geolocation, and behavioral analysis to differentiate between genuine duress and fraudulent claims. This research contributes the first systematic technical solution for coercion-based financial crimes, provides implementation guidance for banking institutions, and establishes foundations for regulatory frameworks governing duress-aware transactions, with particular relevance for emerging markets experiencing high rates of coercive financial crimes.\u003c/p\u003e","manuscriptTitle":"A Duress-Enabled Mobile Banking System for Coercion-Resistant Transactions","msid":"","msnumber":"","nonDraftVersions":[{"code":1,"date":"2025-12-24 11:44:48","doi":"10.21203/rs.3.rs-8279747/v1","editorialEvents":[{"type":"communityComments","content":0},{"type":"decision","content":"Revision requested","date":"2026-03-31T10:31:59+00:00","index":"","fulltext":""},{"type":"editorInvitedReview","content":"","date":"2026-03-29T12:38:11+00:00","index":"hide","fulltext":""},{"type":"editorInvitedReview","content":"","date":"2026-03-23T23:27:26+00:00","index":"hide","fulltext":""},{"type":"editorInvitedReview","content":"","date":"2026-03-12T10:01:45+00:00","index":"hide","fulltext":""},{"type":"editorInvitedReview","content":"","date":"2026-03-11T20:23:37+00:00","index":"hide","fulltext":""},{"type":"reviewerAgreed","content":"273638766278708880553234023029913800466","date":"2026-03-11T19:48:48+00:00","index":"hide","fulltext":""},{"type":"reviewerAgreed","content":"65449415054367894143614185679332848384","date":"2026-03-05T16:14:17+00:00","index":"hide","fulltext":""},{"type":"reviewerAgreed","content":"35281597944817394687177988483248658119","date":"2026-03-03T17:05:25+00:00","index":"hide","fulltext":""},{"type":"reviewerAgreed","content":"127504747933222737440350492597755689948","date":"2026-01-15T09:51:29+00:00","index":"hide","fulltext":""},{"type":"reviewerAgreed","content":"295179408736848728471568523901089498106","date":"2025-12-22T15:44:17+00:00","index":"hide","fulltext":""},{"type":"reviewersInvited","content":"","date":"2025-12-22T12:18:15+00:00","index":"","fulltext":""},{"type":"editorAssigned","content":"","date":"2025-12-09T08:22:13+00:00","index":"","fulltext":""},{"type":"checksComplete","content":"","date":"2025-12-08T19:46:10+00:00","index":"","fulltext":""},{"type":"submitted","content":"Human-Centric Intelligent Systems","date":"2025-12-04T13:06:34+00:00","index":"","fulltext":""}],"status":"published","journal":{"display":true,"email":"[email protected]","identity":"humancentric-intelligent-systems","isNatureJournal":false,"hasQc":true,"allowDirectSubmit":false,"externalIdentity":"","sideBox":"Learn more about [Human-Centric Intelligent Systems](https://link.springer.com/journal/44230)","snPcode":"44230","submissionUrl":"https://submission.springernature.com/new-submission/44230/3","title":"Human-Centric Intelligent Systems","twitterHandle":"","acdcEnabled":true,"dfaEnabled":true,"editorialSystem":"stoa","reportingPortfolio":"Springer Open","inReviewEnabled":true,"inReviewRevisionsEnabled":true}}],"origin":"","ownerIdentity":"d1956d23-09ec-4ed0-a269-278c297ea117","owner":[],"postedDate":"December 24th, 2025","published":true,"recentEditorialEvents":[],"rejectedJournal":[],"revision":"","amendment":"","status":"under-review","subjectAreas":[],"tags":[],"updatedAt":"2026-05-05T14:09:01+00:00","versionOfRecord":[],"versionCreatedAt":"2025-12-24 11:44:48","video":"","vorDoi":"","vorDoiUrl":"","workflowStages":[]},"version":"v1","identity":"rs-8279747","journalConfig":"researchsquare"},"__N_SSP":true},"page":"/article/[identity]/[[...version]]","query":{"redirect":"/article/rs-8279747","identity":"rs-8279747","version":["v1"]},"buildId":"XKTyCvWXoU3ODBz1xrDgd","isFallback":false,"isExperimentalCompile":false,"dynamicIds":[84888],"gssp":true,"scriptLoader":[]}