Protecting Collaborative Education: A Blockchain-Powered Trust and Reward System to Reduce Poisoning Attacks in Federated Learning

Protecting Collaborative Education: A Blockchain-Powered Trust and Reward System to Reduce Poisoning Attacks in Federated Learning | 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 Protecting Collaborative Education: A Blockchain-Powered Trust and Reward System to Reduce Poisoning Attacks in Federated Learning Din Mohammad Toufik This is a preprint; it has not been peer reviewed by a journal. https://doi.org/ 10.21203/rs.3.rs-9305687/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 Federated Learning (FL) is a game-changing idea in education that enables institutions to create robust AI models for individualized learning while maintaining the highest level of privacy for student data. However, due to its decentralized nature, Federated Education is very vulnerable to Poisoning Attacks (data and model poisoning), where nodes are compromised to provide false information to the global model, causing a substantial decline in its accuracy. This research aims to introduce a special Blockchain-based Trust Management and Incentive Framework for Federated Education to address this critical security threat. Our proposed design is a dynamic and decentralized system of reputation, facilitated by self-executing Smart Contracts and cryptographic validation. Real-time trust scores are generated based on an assessment of the dependability of each participating node in the past, in addition to cryptographic validation of learning. Although malevolent nodes that launch poisoning attacks are easily identified, penalized, and excluded from the aggregation, honest and contributing institutions with high-quality and localized updates to models are algorithmically rewarded with tokenized incentives. Based on preliminary simulations, our blockchain-based system is able to counter targeted poisoning attacks, with a global model accuracy of over 95% maintained even with up to 30% compromised nodes, while traditional FL models see a considerable reduction in accuracy (up to 30-40%) with 15% malicious nodes. This proposed system for the future of AI in education is not only able to counter negative threats but is also in a position to foster a system that is transparent, sustainable, and highly collaborative. Artificial Intelligence and 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-9305687","acceptedTermsAndConditions":true,"allowDirectSubmit":true,"archivedVersions":[],"articleType":"Research Article","associatedPublications":[],"authors":[{"id":616765717,"identity":"82396ae4-1478-48ca-a7ea-1f3d986a1870","order_by":0,"name":"Din Mohammad Toufik","email":"data:image/png;base64,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","orcid":"https://orcid.org/0009-0005-5603-874X","institution":"Metopolitan University, Sylhet, Bangladesh","correspondingAuthor":true,"prefix":"","firstName":"Din","middleName":"Mohammad","lastName":"Toufik","suffix":""}],"badges":[],"createdAt":"2026-04-02 17:00:58","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-9305687/v1","doiUrl":"https://doi.org/10.21203/rs.3.rs-9305687/v1","draftVersion":[],"editorialEvents":[],"editorialNote":"","failedWorkflow":false,"files":[{"id":106723814,"identity":"2e4bcd22-4313-480f-ad69-b89d1bfbc834","added_by":"auto","created_at":"2026-04-12 18:15:42","extension":"pdf","order_by":1,"title":"","display":"","copyAsset":false,"role":"manuscript-pdf","size":520425,"visible":true,"origin":"","legend":"","description":"","filename":"FederatedLearning.pdf","url":"https://assets-eu.researchsquare.com/files/rs-9305687/v1_covered_26c4d2bb-f858-4387-ba72-fa7e5ae6096f.pdf"}],"financialInterests":"The authors declare no competing interests.","formattedTitle":"\u003cp\u003e\u003cstrong\u003eProtecting Collaborative Education: A Blockchain-Powered Trust and Reward System to Reduce Poisoning Attacks in Federated Learning\u003c/strong\u003e\u003c/p\u003e","fulltext":[],"fulltextSource":"","fullText":"","funders":[],"hasAdminPriorityOnWorkflow":false,"hasManuscriptDocX":false,"hasOptedInToPreprint":true,"hasPassedJournalQc":"","hasAnyPriority":true,"hideJournal":true,"highlight":"","institution":"Metropolitan University, Sylhet, Bangladesh","isAcceptedByJournal":false,"isAuthorSuppliedPdf":true,"isDeskRejected":"","isHiddenFromSearch":false,"isInQc":false,"isInWorkflow":false,"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":"","lastPublishedDoi":"10.21203/rs.3.rs-9305687/v1","lastPublishedDoiUrl":"https://doi.org/10.21203/rs.3.rs-9305687/v1","license":{"name":"CC BY 4.0","url":"https://creativecommons.org/licenses/by/4.0/"},"manuscriptAbstract":"\u003cp\u003eFederated Learning (FL) is a game-changing idea in education that enables institutions to create robust AI models for individualized learning while maintaining the highest level of privacy for student data. However, due to its decentralized nature, Federated Education is very vulnerable to Poisoning Attacks (data and model poisoning), where nodes are compromised to provide false information to the global model, causing a substantial decline in its accuracy. This research aims to introduce a special Blockchain-based Trust Management and Incentive Framework for Federated Education to address this critical security threat.\u003c/p\u003e\n\u003cp\u003eOur proposed design is a dynamic and decentralized system of reputation, facilitated by self-executing Smart Contracts and cryptographic validation. Real-time trust scores are generated based on an assessment of the dependability of each participating node in the past, in addition to cryptographic validation of learning. Although malevolent nodes that launch poisoning attacks are easily identified, penalized, and excluded from the aggregation, honest and contributing institutions with high-quality and localized updates to models are algorithmically rewarded with tokenized incentives. Based on preliminary simulations, our blockchain-based system is able to counter targeted poisoning attacks, with a global model accuracy of over 95% maintained even with up to 30% compromised nodes, while traditional FL models see a considerable reduction in accuracy (up to 30-40%) with 15% malicious nodes. This proposed system for the future of AI in education is not only able to counter negative threats but is also in a position to foster a system that is transparent, sustainable, and highly collaborative.\u003c/p\u003e","manuscriptTitle":"Protecting Collaborative Education: A Blockchain-Powered Trust and Reward System to Reduce Poisoning Attacks in Federated Learning","msid":"","msnumber":"","nonDraftVersions":[{"code":1,"date":"2026-04-03 10:27:36","doi":"10.21203/rs.3.rs-9305687/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":"00d286eb-7139-4b9a-acec-7a93e8dd1b69","owner":[],"postedDate":"April 3rd, 2026","published":true,"recentEditorialEvents":[],"rejectedJournal":[],"revision":"","amendment":"","status":"posted","subjectAreas":[{"id":65635176,"name":"Artificial Intelligence and Machine Learning"}],"tags":[],"updatedAt":"2026-04-03T10:27:36+00:00","versionOfRecord":[],"versionCreatedAt":"2026-04-03 10:27:36","video":"","vorDoi":"","vorDoiUrl":"","workflowStages":[]},"version":"v1","identity":"rs-9305687","journalConfig":"researchsquare"},"__N_SSP":true},"page":"/article/[identity]/[[...version]]","query":{"redirect":"/article/rs-9305687","identity":"rs-9305687","version":["v1"]},"buildId":"XKTyCvWXoU3ODBz1xrDgd","isFallback":false,"isExperimentalCompile":false,"dynamicIds":[84888],"gssp":true,"scriptLoader":[]}