MerkleFL: A Secure Decentralized Federated Learning Framework for Healthcare with Model Integrity Verification

MerkleFL: A Secure Decentralized Federated Learning Framework for Healthcare with Model Integrity Verification | 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 MerkleFL: A Secure Decentralized Federated Learning Framework for Healthcare with Model Integrity Verification Ashwin Verma, Sunil Pathak, Pronaya Bhattacharya This is a preprint; it has not been peer reviewed by a journal. https://doi.org/ 10.21203/rs.3.rs-6933179/v1 This work is licensed under a CC BY 4.0 License Status: Under Review Version 1 posted 18 You are reading this latest preprint version Abstract Decentralized federated learning (DFL) offers a privacy-preserving approach for collaboratively training models across distributed healthcare entities without sharing raw patient data. However, ensuring the integrity and reliability of model updates in such decentralized settings remains a significant challenge. This paper introduces \textit{MerkleFL}, a secure and efficient DFL framework that integrates cluster-based aggregation with Merkle Tree-based verification to detect and reject tampered or unauthorized model contributions. The proposed system employs a lightweight integrity-checking mechanism where each model update is associated with a cryptographic Merkle Root, enabling trustless verification at the cluster level. A dynamic leader election protocol facilitates intra-cluster coordination without relying on central servers or blockchain consensus. Experimental evaluations conducted on the NIH ChestX-ray14 dataset demonstrate that MerkleFL achieves faster convergence, higher classification accuracy, and lower training loss compared to existing DFL schemes such as Gossip-DFL, Ring-DFL, and Blockchain-DFL. The results confirm that MerkleFL effectively balances security, scalability, and performance, making it a practical solution for federated healthcare AI applications. Decentralized Federated Learning Peer-to-Peer Learning Federated Learning Model integrity verification Merkle Tree Full Text Additional Declarations No competing interests reported. Cite Share Download PDF Status: Under Review Version 1 posted Reviews received at journal 19 May, 2026 Reviews received at journal 18 May, 2026 Reviewers agreed at journal 11 May, 2026 Reviewers agreed at journal 10 May, 2026 Reviewers agreed at journal 08 May, 2026 Reviews received at journal 07 May, 2026 Reviews received at journal 07 May, 2026 Reviewers agreed at journal 07 May, 2026 Reviewers agreed at journal 06 May, 2026 Reviewers agreed at journal 05 May, 2026 Reviewers agreed at journal 05 May, 2026 Reviewers agreed at journal 05 May, 2026 Reviewers agreed at journal 05 May, 2026 Reviewers agreed at journal 05 May, 2026 Reviewers invited by journal 05 May, 2026 Editor assigned by journal 21 Jun, 2025 Submission checks completed at journal 21 Jun, 2025 First submitted to journal 19 Jun, 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-6933179","acceptedTermsAndConditions":true,"allowDirectSubmit":false,"archivedVersions":[],"articleType":"Research Article","associatedPublications":[],"authors":[{"id":638519398,"identity":"58a85c86-e027-4c10-9ea6-e43feda82601","order_by":0,"name":"Ashwin Verma","email":"","orcid":"","institution":"Amity University Jaipur","correspondingAuthor":false,"prefix":"","firstName":"Ashwin","middleName":"","lastName":"Verma","suffix":""},{"id":638519399,"identity":"524ebcde-5ab2-4d8e-ae94-dbd4e3df756d","order_by":1,"name":"Sunil Pathak","email":"","orcid":"","institution":"Amity University Jaipur","correspondingAuthor":false,"prefix":"","firstName":"Sunil","middleName":"","lastName":"Pathak","suffix":""},{"id":638519401,"identity":"8157ccf9-4860-483d-8b20-f4c92efeb0a8","order_by":2,"name":"Pronaya Bhattacharya","email":"data:image/png;base64,iVBORw0KGgoAAAANSUhEUgAAAZAAAAAyAQMAAABI0h/eAAAABlBMVEX///8AAABVwtN+AAAACXBIWXMAAA7EAAAOxAGVKw4bAAABIUlEQVRIiWNgGAWjYDACCR4IbQAmKxIY+EB0AgOCxKrlQAJMy5kEBjaw4gRitTC2QbUw4NFiLt178PPHH3by5uxnn0n8nJcmx8bA/HTDwx+HGfjZcwywabGccy5Z4kBCsuHOnnQzyd5tOcZsDGxmNxISDjNI9rzBqsXgRo4BUAtzgsGBNDYJ3m0ViW0MDBAtICkcWox/HEioTzA4/4xN8u8ckBb2b2At9ri1mAFtOZxgcCONTZq3IQeohQdqiwQuv5wxsziTdtxww41nzNYyx9KM2Zh5ym4kpKXzSJx5VoA9xHqMb1TYVMsbnE9jvPmmJlmOn719280fNtZy/O3JG7A6DInNIgGmmMFkMw825ehamD8gcepw6RgFo2AUjIKRBwB65WPyIRTrJAAAAABJRU5ErkJggg==","orcid":"","institution":"Amity University","correspondingAuthor":true,"prefix":"","firstName":"Pronaya","middleName":"","lastName":"Bhattacharya","suffix":""}],"badges":[],"createdAt":"2025-06-19 17:08:12","currentVersionCode":1,"declarations":"","doi":"10.21203/rs.3.rs-6933179/v1","doiUrl":"https://doi.org/10.21203/rs.3.rs-6933179/v1","draftVersion":[],"editorialEvents":[],"editorialNote":"","failedWorkflow":false,"files":[{"id":109206107,"identity":"7d28ac8d-1bca-4000-ab89-5cf259d14e1f","added_by":"auto","created_at":"2026-05-13 15:11:11","extension":"pdf","order_by":1,"title":"","display":"","copyAsset":false,"role":"manuscript-pdf","size":1343864,"visible":true,"origin":"","legend":"","description":"","filename":"MERKLEFLSPRINGER.pdf","url":"https://assets-eu.researchsquare.com/files/rs-6933179/v1_covered_4286bd43-60b6-4481-b0e8-d3f1461e077c.pdf"}],"financialInterests":"No competing interests reported.","formattedTitle":"\u003cp\u003eMerkleFL: A Secure Decentralized Federated Learning Framework for Healthcare with Model Integrity Verification\u003c/p\u003e","fulltext":[],"fulltextSource":"","fullText":"","funders":[],"hasAdminPriorityOnWorkflow":false,"hasManuscriptDocX":false,"hasOptedInToPreprint":true,"hasPassedJournalQc":"","hasAnyPriority":false,"hideJournal":false,"highlight":"","institution":"","isAcceptedByJournal":false,"isAuthorSuppliedPdf":true,"isDeskRejected":"","isHiddenFromSearch":false,"isInQc":false,"isInWorkflow":false,"isPdf":true,"isPdfUpToDate":true,"isWithdrawnOrRetracted":false,"journal":{"display":true,"email":"[email protected]","identity":"the-journal-of-supercomputing","isNatureJournal":false,"hasQc":true,"allowDirectSubmit":false,"externalIdentity":"","sideBox":"Learn more about [The Journal of Supercomputing](https://www.springer.com/journal/11227)","snPcode":"11227","submissionUrl":"https://submission.nature.com/new-submission/11227/3","title":"The Journal of Supercomputing","twitterHandle":"","acdcEnabled":true,"dfaEnabled":true,"editorialSystem":"stoa","reportingPortfolio":"Springer Hybrid","inReviewEnabled":true,"inReviewRevisionsEnabled":false},"keywords":"Decentralized Federated Learning, Peer-to-Peer Learning, Federated Learning, Model integrity verification, Merkle Tree","lastPublishedDoi":"10.21203/rs.3.rs-6933179/v1","lastPublishedDoiUrl":"https://doi.org/10.21203/rs.3.rs-6933179/v1","license":{"name":"CC BY 4.0","url":"https://creativecommons.org/licenses/by/4.0/"},"manuscriptAbstract":"Decentralized federated learning (DFL) offers a privacy-preserving approach for collaboratively training models across distributed healthcare entities without sharing raw patient data. However, ensuring the integrity and reliability of model updates in such decentralized settings remains a significant challenge. This paper introduces \\textit{MerkleFL}, a secure and efficient DFL framework that integrates cluster-based aggregation with Merkle Tree-based verification to detect and reject tampered or unauthorized model contributions. The proposed system employs a lightweight integrity-checking mechanism where each model update is associated with a cryptographic Merkle Root, enabling trustless verification at the cluster level. A dynamic leader election protocol facilitates intra-cluster coordination without relying on central servers or blockchain consensus. Experimental evaluations conducted on the NIH ChestX-ray14 dataset demonstrate that MerkleFL achieves faster convergence, higher classification accuracy, and lower training loss compared to existing DFL schemes such as Gossip-DFL, Ring-DFL, and Blockchain-DFL. The results confirm that MerkleFL effectively balances security, scalability, and performance, making it a practical solution for federated healthcare AI applications.","manuscriptTitle":"MerkleFL: A Secure Decentralized Federated Learning Framework for Healthcare with Model Integrity Verification","msid":"","msnumber":"","nonDraftVersions":[{"code":1,"date":"2026-05-13 11:00:31","doi":"10.21203/rs.3.rs-6933179/v1","editorialEvents":[{"type":"communityComments","content":0},{"type":"editorInvitedReview","content":"","date":"2026-05-19T07:20:49+00:00","index":"hide","fulltext":""},{"type":"editorInvitedReview","content":"","date":"2026-05-18T19:07:45+00:00","index":"hide","fulltext":""},{"type":"reviewerAgreed","content":"40742438419597595795780568397643913724","date":"2026-05-11T19:20:00+00:00","index":"hide","fulltext":""},{"type":"reviewerAgreed","content":"71491632861412038707596817498949837339","date":"2026-05-10T07:13:30+00:00","index":"hide","fulltext":""},{"type":"reviewerAgreed","content":"105542185434027811938865306021772367362","date":"2026-05-08T10:39:45+00:00","index":"hide","fulltext":""},{"type":"editorInvitedReview","content":"","date":"2026-05-07T09:11:28+00:00","index":"hide","fulltext":""},{"type":"editorInvitedReview","content":"","date":"2026-05-07T08:58:32+00:00","index":"hide","fulltext":""},{"type":"reviewerAgreed","content":"158497372774193800706111100495204456521","date":"2026-05-07T08:50:16+00:00","index":"hide","fulltext":""},{"type":"reviewerAgreed","content":"326131595170462156273153589751719713400","date":"2026-05-06T06:04:54+00:00","index":"hide","fulltext":""},{"type":"reviewerAgreed","content":"300796165859102565498174321823411590317","date":"2026-05-06T02:13:28+00:00","index":"hide","fulltext":""},{"type":"reviewerAgreed","content":"251528989345712419424052649202720240746","date":"2026-05-06T01:10:40+00:00","index":"hide","fulltext":""},{"type":"reviewerAgreed","content":"327194268775720904631890198766198304378","date":"2026-05-06T00:55:45+00:00","index":"hide","fulltext":""},{"type":"reviewerAgreed","content":"221604684843839306640742869799619884438","date":"2026-05-05T23:56:33+00:00","index":"hide","fulltext":""},{"type":"reviewerAgreed","content":"94091359241854481862885888665813988927","date":"2026-05-05T22:14:59+00:00","index":"hide","fulltext":""},{"type":"reviewersInvited","content":"","date":"2026-05-05T21:13:56+00:00","index":"","fulltext":""},{"type":"editorAssigned","content":"","date":"2025-06-21T16:16:58+00:00","index":"","fulltext":""},{"type":"checksComplete","content":"","date":"2025-06-21T16:16:44+00:00","index":"","fulltext":""},{"type":"submitted","content":"The Journal of Supercomputing","date":"2025-06-19T16:57:14+00:00","index":"","fulltext":""}],"status":"published","journal":{"display":true,"email":"[email protected]","identity":"the-journal-of-supercomputing","isNatureJournal":false,"hasQc":true,"allowDirectSubmit":false,"externalIdentity":"","sideBox":"Learn more about [The Journal of Supercomputing](https://www.springer.com/journal/11227)","snPcode":"11227","submissionUrl":"https://submission.nature.com/new-submission/11227/3","title":"The Journal of Supercomputing","twitterHandle":"","acdcEnabled":true,"dfaEnabled":true,"editorialSystem":"stoa","reportingPortfolio":"Springer Hybrid","inReviewEnabled":true,"inReviewRevisionsEnabled":false}}],"origin":"","ownerIdentity":"e46ad94d-15e4-4fd4-95fc-904d37735761","owner":[],"postedDate":"May 13th, 2026","published":true,"recentEditorialEvents":[{"type":"editorInvitedReview","content":"","date":"2026-05-19T07:20:49+00:00","index":146,"fulltext":""},{"type":"editorInvitedReview","content":"","date":"2026-05-18T19:07:45+00:00","index":145,"fulltext":""},{"type":"reviewerAgreed","content":"40742438419597595795780568397643913724","date":"2026-05-11T19:20:00+00:00","index":144,"fulltext":""},{"type":"reviewerAgreed","content":"71491632861412038707596817498949837339","date":"2026-05-10T07:13:30+00:00","index":143,"fulltext":""},{"type":"reviewerAgreed","content":"105542185434027811938865306021772367362","date":"2026-05-08T10:39:45+00:00","index":142,"fulltext":""},{"type":"editorInvitedReview","content":"","date":"2026-05-07T09:11:28+00:00","index":135,"fulltext":""},{"type":"editorInvitedReview","content":"","date":"2026-05-07T08:58:32+00:00","index":134,"fulltext":""},{"type":"reviewerAgreed","content":"158497372774193800706111100495204456521","date":"2026-05-07T08:50:16+00:00","index":133,"fulltext":""},{"type":"reviewerAgreed","content":"326131595170462156273153589751719713400","date":"2026-05-06T06:04:54+00:00","index":129,"fulltext":""},{"type":"reviewerAgreed","content":"300796165859102565498174321823411590317","date":"2026-05-06T02:13:28+00:00","index":128,"fulltext":""},{"type":"reviewerAgreed","content":"251528989345712419424052649202720240746","date":"2026-05-06T01:10:40+00:00","index":127,"fulltext":""},{"type":"reviewerAgreed","content":"327194268775720904631890198766198304378","date":"2026-05-06T00:55:45+00:00","index":126,"fulltext":""},{"type":"reviewerAgreed","content":"221604684843839306640742869799619884438","date":"2026-05-05T23:56:33+00:00","index":124,"fulltext":""},{"type":"reviewerAgreed","content":"94091359241854481862885888665813988927","date":"2026-05-05T22:14:59+00:00","index":123,"fulltext":""},{"type":"reviewersInvited","content":"117","date":"2026-05-05T21:13:56+00:00","index":"","fulltext":""}],"rejectedJournal":[],"revision":"","amendment":"","status":"under-review","subjectAreas":[],"tags":[],"updatedAt":"2026-05-13T11:00:31+00:00","versionOfRecord":[],"versionCreatedAt":"2026-05-13 11:00:31","video":"","vorDoi":"","vorDoiUrl":"","workflowStages":[]},"version":"v1","identity":"rs-6933179","journalConfig":"researchsquare"},"__N_SSP":true},"page":"/article/[identity]/[[...version]]","query":{"redirect":"/article/rs-6933179","identity":"rs-6933179","version":["v1"]},"buildId":"XKTyCvWXoU3ODBz1xrDgd","isFallback":false,"isExperimentalCompile":false,"dynamicIds":[84888],"gssp":true,"scriptLoader":[]}