Dejavu Forensic: Using Support Vector Machine to Improve Recovery Results for Formatted Data in JPEG and PNG Extensions

Dejavu Forensic: Using Support Vector Machine to Improve Recovery Results for Formatted Data in JPEG and PNG Extensions | 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 Dejavu Forensic: Using Support Vector Machine to Improve Recovery Results for Formatted Data in JPEG and PNG Extensions Islan Amorim Bezerra, Sidney Marlon Lopes de Lima, Rubens Karman Paula da Silva This is a preprint; it has not been peer reviewed by a journal. https://doi.org/ 10.21203/rs.3.rs-4731277/v1 This work is licensed under a CC BY 4.0 License Status: Posted Version 1 posted You are reading this latest preprint version Abstract Background : In line with technological advances, virtual crimes have a greater tendency to occur. The most routine situations are: cyberbullying and illicit sharing, but cases of invasion of privacy, dissemination of defamatory emails and child pornography also occur. When digital equipment is stolen, lost or disposed of, data is still stored on disks. This factor enables the recovery of this file. Objective : The main focus of this article is the recovery of formatted files. The applicability of Foremost, Scalpel and Magic Rescue tools in the Linux environment is investigated. In addition, an authorial tool, equipped with machine learning, is used. The general objective of this research is to develop a recovery and validation tool for formatted files. The project aims to contribute to investigations of digital and cyber crimes. In addition to demonstrating knowledge, it brings new perceptions of analysis with regard to recovery methods for formatted files. Methods : Using the pattern recognition methodology, the cluster is used as input, which, through the histogram, acts as an input neuron of the learning machine. This work applies machine learning aiming at recognizing the pattern of the blocks/clusters. In the first scenario, here named “simple”, the classification is binary. There is only class vs. counterclass. This methodology was developed by Pavel (2017) and replicated in the aforementioned simple scenario. In a second scenario, named “complex”, the one-against-all method was used, whose database contains 16,000 files. Results : This research presents a cutting-edge approach that synergizes machine learning and data science to recover formatted data. Our innovative tool boasts a remarkable recovery rate of over 96% for formatted PNG and JPEG files, running in just a few seconds. This breakthrough holds significant promise for improving digital forensic investigations. Conclusions : The experiences declared in the proposed work leave contributions for the advancement in studies about data recovery. Its relevance concerns the proposal to assist in the elucidation of digital crimes that surround the society of digital natives. The authorial system becomes a locus of how technology can serve human rights and improve the quality of life in contemporary society. Artificial Intelligence and Machine Learning Data carving Digital Forensics Cybercrime Data Recovery Machine Learning Full Text Additional Declarations The authors declare no competing interests. Cite Share Download PDF Status: Posted Version 1 posted You are reading this latest preprint version Research Square lets you share your work early, gain feedback from the community, and start making changes to your manuscript prior to peer review in a journal. As a division of Research Square Company, we’re committed to making research communication faster, fairer, and more useful. We do this by developing innovative software and high quality services for the global research community. Our growing team is made up of researchers and industry professionals working together to solve the most critical problems facing scientific publishing. Also discoverable on Platform About Our Team In Review Editorial Policies Advisory Board Help Center Resources Author Services Accessibility API Access RSS feed Manage Cookie Preferences © Research Square 2026 | ISSN 2693-5015 (online) Privacy Policy Terms of Service Do Not Sell My Personal Information {"props":{"pageProps":{"initialData":{"identity":"rs-4731277","acceptedTermsAndConditions":true,"allowDirectSubmit":true,"archivedVersions":[],"articleType":"Research Article","associatedPublications":[],"authors":[{"id":326233984,"identity":"47661eb1-3beb-40c0-bd09-349f6128b360","order_by":0,"name":"Islan Amorim Bezerra","email":"data:image/png;base64,iVBORw0KGgoAAAANSUhEUgAAAZAAAAAyAQMAAABI0h/eAAAABlBMVEX///8AAABVwtN+AAAACXBIWXMAAA7EAAAOxAGVKw4bAAAA2UlEQVRIiWNgGAWjYBACNgbmBiiTsYHhA4iWIKiFEaGFcQYxWhgQWhgYmHmI0cLHf7DxcwGDXTS/9OHWzbZtd+QYpHsf4HeYRGKz9AyG5NyZfYltt3PbnhkzyBw3IKCFsUGah4E5d8MZRpCWw4kNEmn4HcbGf7D5Nw9DPUSLZdvhesJaGBLbgLYchmhhbDucwEBQi0RimzWPwfHcmT2MbTd7zj0zbJM5hl+LfP/hw7d5Kqpz+3nYn934UXZHnl+6Db8WCEAE0QGgU0kEB0jVMApGwSgYBSMAAAA8mEIaYImzRwAAAABJRU5ErkJggg==","orcid":"https://orcid.org/0000-0002-8920-6691","institution":"Universidade de Pernambuco","correspondingAuthor":true,"prefix":"","firstName":"Islan","middleName":"Amorim","lastName":"Bezerra","suffix":""},{"id":326233985,"identity":"7f4ac8c3-4a83-4955-92e3-12585ccb3734","order_by":1,"name":"Sidney Marlon Lopes de Lima","email":"","orcid":"https://orcid.org/0000-0002-4350-9689","institution":"Universidade de Pernambuco","correspondingAuthor":false,"prefix":"","firstName":"Sidney","middleName":"Marlon Lopes","lastName":"de Lima","suffix":""},{"id":326233986,"identity":"f8f5b0bb-ff75-4425-b7b0-98cd498cfa25","order_by":2,"name":"Rubens Karman Paula da Silva","email":"","orcid":"https://orcid.org/0000-0001-9388-9889","institution":"Universidade de Pernambuco","correspondingAuthor":false,"prefix":"","firstName":"Rubens","middleName":"Karman Paula da","lastName":"Silva","suffix":""}],"badges":[],"createdAt":"2024-07-12 15:29:11","currentVersionCode":1,"declarations":{"humanSubjects":false,"vertebrateSubjects":false,"conflictsOfInterestStatement":false,"humanSubjectEthicalGuidelines":false,"humanSubjectConsent":false,"humanSubjectClinicalTrial":false,"humanSubjectCaseReport":false,"vertebrateSubjectEthicalGuidelines":false},"doi":"10.21203/rs.3.rs-4731277/v1","doiUrl":"https://doi.org/10.21203/rs.3.rs-4731277/v1","draftVersion":[],"editorialEvents":[],"editorialNote":"","failedWorkflow":false,"files":[{"id":60363322,"identity":"e9924cd3-bfb2-4e9c-91c6-578d8e3a27d2","added_by":"auto","created_at":"2024-07-16 03:03:14","extension":"pdf","order_by":1,"title":"","display":"","copyAsset":false,"role":"manuscript-pdf","size":1440490,"visible":true,"origin":"","legend":"","description":"","filename":"DejavuForensicUsingSupportVectorMachine.pdf","url":"https://assets-eu.researchsquare.com/files/rs-4731277/v1_covered_c5a5b25e-2ff8-48d7-b9f8-3afec662cd7c.pdf"}],"financialInterests":"The authors declare no competing interests.","formattedTitle":"\u003cp\u003eDejavu Forensic: Using Support Vector Machine to Improve Recovery Results for Formatted Data in JPEG and PNG Extensions\u003c/p\u003e","fulltext":[],"fulltextSource":"","fullText":"","funders":[],"hasAdminPriorityOnWorkflow":false,"hasManuscriptDocX":false,"hasOptedInToPreprint":true,"hasPassedJournalQc":"","hasAnyPriority":true,"hideJournal":true,"highlight":"","institution":"Universidade de Pernambuco","isAcceptedByJournal":false,"isAuthorSuppliedPdf":true,"isDeskRejected":"","isHiddenFromSearch":false,"isInQc":false,"isInWorkflow":true,"isPdf":true,"isPdfUpToDate":true,"isWithdrawnOrRetracted":false,"journal":{"display":true,"email":"[email protected]","identity":"researchsquare","isNatureJournal":false,"hasQc":true,"allowDirectSubmit":true,"externalIdentity":"","sideBox":"","snPcode":"","submissionUrl":"/submission","title":"Research Square","twitterHandle":"researchsquare","acdcEnabled":true,"dfaEnabled":false,"editorialSystem":"","reportingPortfolio":"","inReviewEnabled":false,"inReviewRevisionsEnabled":true},"keywords":"Data carving, Digital Forensics, Cybercrime, Data Recovery, Machine Learning","lastPublishedDoi":"10.21203/rs.3.rs-4731277/v1","lastPublishedDoiUrl":"https://doi.org/10.21203/rs.3.rs-4731277/v1","license":{"name":"CC BY 4.0","url":"https://creativecommons.org/licenses/by/4.0/"},"manuscriptAbstract":"\u003cp\u003e\u003cstrong\u003eBackground\u003c/strong\u003e: In line with technological advances, virtual crimes have a greater tendency to occur. The most routine situations are: cyberbullying and illicit sharing, but cases of invasion of privacy, dissemination of defamatory emails and child pornography also occur. When digital equipment is stolen, lost or disposed of, data is still stored on disks. This factor enables the recovery of this file.\u003c/p\u003e\n\u003cp\u003e\u003cstrong\u003eObjective\u003c/strong\u003e: The main focus of this article is the recovery of formatted files. The applicability of Foremost, Scalpel and Magic Rescue tools in the Linux environment is investigated. In addition, an authorial tool, equipped with machine learning, is used. The general objective of this research is to develop a recovery and validation tool for formatted files. The project aims to contribute to investigations of digital and cyber crimes. In addition to demonstrating knowledge, it brings new perceptions of analysis with regard to recovery methods for formatted files.\u003c/p\u003e\n\u003cp\u003e\u003cstrong\u003eMethods\u003c/strong\u003e: Using the pattern recognition methodology, the cluster is used as input, which, through the histogram, acts as an input neuron of the learning machine. This work applies machine learning aiming at recognizing the pattern of the blocks/clusters. In the first scenario, here named “simple”, the classification is binary. There is only class vs. counterclass. This methodology was developed by Pavel (2017) and replicated in the aforementioned simple scenario. In a second scenario, named “complex”, the one-against-all method was used, whose database contains 16,000 files.\u003c/p\u003e\n\u003cp\u003e\u003cstrong\u003eResults\u003c/strong\u003e: This research presents a cutting-edge approach that synergizes machine learning and data science to recover formatted data. Our innovative tool boasts a remarkable recovery rate of over 96% for formatted PNG and JPEG files, running in just a few seconds. This breakthrough holds significant promise for improving digital forensic investigations.\u003c/p\u003e\n\u003cp\u003e\u003cstrong\u003eConclusions\u003c/strong\u003e: The experiences declared in the proposed work leave contributions for the advancement in studies about data recovery. Its relevance concerns the proposal to assist in the elucidation of digital crimes that surround the society of digital natives. The authorial system becomes a locus of how technology can serve human rights and improve the quality of life in contemporary society.\u003c/p\u003e","manuscriptTitle":"Dejavu Forensic: Using Support Vector Machine to Improve Recovery Results for Formatted Data in JPEG and PNG Extensions","msid":"","msnumber":"","nonDraftVersions":[{"code":1,"date":"2024-07-16 02:55:07","doi":"10.21203/rs.3.rs-4731277/v1","editorialEvents":[{"type":"communityComments","content":0}],"status":"published","journal":{"display":true,"email":"[email protected]","identity":"researchsquare","isNatureJournal":false,"hasQc":true,"allowDirectSubmit":true,"externalIdentity":"","sideBox":"","snPcode":"","submissionUrl":"/submission","title":"Research Square","twitterHandle":"researchsquare","acdcEnabled":true,"dfaEnabled":false,"editorialSystem":"","reportingPortfolio":"","inReviewEnabled":false,"inReviewRevisionsEnabled":true}}],"origin":"","ownerIdentity":"8bfb4881-52fc-4399-ae0e-3349e084f223","owner":[],"postedDate":"July 16th, 2024","published":true,"recentEditorialEvents":[],"rejectedJournal":[],"revision":"","amendment":"","status":"posted","subjectAreas":[{"id":34524770,"name":"Artificial Intelligence and Machine Learning"}],"tags":[],"updatedAt":"2024-07-16T02:55:07+00:00","versionOfRecord":[],"versionCreatedAt":"2024-07-16 02:55:07","video":"","vorDoi":"","vorDoiUrl":"","workflowStages":[]},"version":"v1","identity":"rs-4731277","journalConfig":"researchsquare"},"__N_SSP":true},"page":"/article/[identity]/[[...version]]","query":{"redirect":"/article/rs-4731277","identity":"rs-4731277","version":["v1"]},"buildId":"qtupq5eGEP_6zYnWcrvyt","isFallback":false,"isExperimentalCompile":false,"dynamicIds":[84888],"gssp":true,"scriptLoader":[]}