Multi-Level Defense Strategy for Vertical Federated Learning Against Label Inference Attacks

Multi-Level Defense Strategy for Vertical Federated Learning Against Label Inference Attacks | 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 Multi-Level Defense Strategy for Vertical Federated Learning Against Label Inference Attacks Linlong Wang, Chungen Xu, Pan Zhang, Yiting Liu This is a preprint; it has not been peer reviewed by a journal. https://doi.org/ 10.21203/rs.3.rs-4679192/v1 This work is licensed under a CC BY 4.0 License Status: Under Review Version 1 posted 2 You are reading this latest preprint version Abstract Vertical federated learning (VFL) is increasingly recognized as an indispensable paradigm. Especially in the medical field, where the protection of data privacy plays an indispensable role. In the healthcare domain, adherence to stringent regulatory frameworks such as GDPR and HIPAA is indispensable. VFL facilitates a collaborative approach among institutions, enabling the prediction of disease risks without collecting sensitive patient data. However, VFL remains susceptible to label inference attacks, wherein malicious entities may extrapolate personal data from the exchanged intermediate results. To address the above challenge, we propose a strategic mechanism known as the balanced noise injection strategy (BNIS). This strategy is designed to meticulously regulate the introduction of noise, achieving a trade-off between privacy preservation and model accuracy. Moreover, to bolster our framework, we propose the multi-loss defense strategy (MLDS), an innovative defense explicitly engineered to withstand direct label inference attacks with resilience. Extensive evaluations on four benchmark datasets demonstrate that our approach defenses against passive attacks and yields a significant improvement in accuracy compared to the prevailing FL similar gradient (FLSG) benchmark. Furthermore, MLDS concurrently addresses breaches in label inference and greatly enhances the precision of the model. Vertical federated learning Label inference attacks Noise control Privacy protection Full Text Additional Declarations No competing interests reported. Cite Share Download PDF Status: Under Review Version 1 posted Submission checks completed at journal 04 Jul, 2024 First submitted to journal 03 Jul, 2024 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-4679192","acceptedTermsAndConditions":true,"allowDirectSubmit":false,"archivedVersions":[],"articleType":"Research Article","associatedPublications":[],"authors":[{"id":322601968,"identity":"153a1b7d-4b31-48a3-b173-c407b8d804da","order_by":0,"name":"Linlong Wang","email":"","orcid":"","institution":"Nanjing University of Science and Technology","correspondingAuthor":false,"prefix":"","firstName":"Linlong","middleName":"","lastName":"Wang","suffix":""},{"id":322601969,"identity":"b72f7bd5-69d9-45a3-9f85-e36e84b62d64","order_by":1,"name":"Chungen Xu","email":"data:image/png;base64,iVBORw0KGgoAAAANSUhEUgAAAZAAAAAyAQMAAABI0h/eAAAABlBMVEX///8AAABVwtN+AAAACXBIWXMAAA7EAAAOxAGVKw4bAAAA00lEQVRIiWNgGAWjYHACNgjF3gAkDCxI0cJzAKRFghQtEglgkrB6gxvJzx7z7qiVM5d8fnXDjwIJBv727gS8WiRnpJkb8545bmw5O6fsZg/QYRJnzm7Aq4VfIodNmrftWOKG2zlpN3iAWgwkcvFrYYNqqd9w80zazT/EaIHaUpNgcIP92G2ibJHseWYmObftgOGGMzlst2UMJHgI+sXgePIzibdtdfIGx48/u/nmj40cf3svfi1QcBiIeQxALB5ilINAHRCzPyBW9SgYBaNgFIwwAAAw00Sp9FxeBQAAAABJRU5ErkJggg==","orcid":"","institution":"Nanjing University of Science and Technology","correspondingAuthor":true,"prefix":"","firstName":"Chungen","middleName":"","lastName":"Xu","suffix":""},{"id":322601970,"identity":"ab165319-9f49-4f7e-af27-4c1a6fcce1eb","order_by":2,"name":"Pan Zhang","email":"","orcid":"","institution":"Nanjing University of Science and Technology","correspondingAuthor":false,"prefix":"","firstName":"Pan","middleName":"","lastName":"Zhang","suffix":""},{"id":322601971,"identity":"18599882-e881-423a-95d1-41e3fd13f0d9","order_by":3,"name":"Yiting Liu","email":"","orcid":"","institution":"Nanjing University of Science and Technology","correspondingAuthor":false,"prefix":"","firstName":"Yiting","middleName":"","lastName":"Liu","suffix":""}],"badges":[],"createdAt":"2024-07-03 09:24:04","currentVersionCode":1,"declarations":"","doi":"10.21203/rs.3.rs-4679192/v1","doiUrl":"https://doi.org/10.21203/rs.3.rs-4679192/v1","draftVersion":[],"editorialEvents":[],"editorialNote":"","failedWorkflow":false,"files":[{"id":61906054,"identity":"a0f2fd92-05f5-42ea-8c48-bed36e37ee96","added_by":"auto","created_at":"2024-08-07 01:41:13","extension":"pdf","order_by":1,"title":"","display":"","copyAsset":false,"role":"manuscript-pdf","size":1302721,"visible":true,"origin":"","legend":"","description":"","filename":"Submit0703.pdf","url":"https://assets-eu.researchsquare.com/files/rs-4679192/v1_covered_bba5b04e-eb5c-4b5e-a3ab-7c4a05b73eb1.pdf"}],"financialInterests":"No competing interests reported.","formattedTitle":"Multi-Level Defense Strategy for Vertical Federated Learning Against Label Inference Attacks","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":"wireless-networks","isNatureJournal":false,"hasQc":true,"allowDirectSubmit":false,"externalIdentity":"wine","sideBox":"Learn more about [Wireless Networks](http://link.springer.com/journal/11276)","snPcode":"11276","submissionUrl":"https://submission.nature.com/new-submission/11276/3","title":"Wireless Networks","twitterHandle":"","acdcEnabled":true,"dfaEnabled":true,"editorialSystem":"stoa","reportingPortfolio":"Springer Hybrid","inReviewEnabled":true,"inReviewRevisionsEnabled":false},"keywords":"Vertical federated learning, Label inference attacks, Noise control, Privacy protection","lastPublishedDoi":"10.21203/rs.3.rs-4679192/v1","lastPublishedDoiUrl":"https://doi.org/10.21203/rs.3.rs-4679192/v1","license":{"name":"CC BY 4.0","url":"https://creativecommons.org/licenses/by/4.0/"},"manuscriptAbstract":"Vertical federated learning (VFL) is increasingly recognized as an indispensable paradigm. Especially in the medical field, where the protection of data privacy plays an indispensable role. In the healthcare domain, adherence to stringent regulatory frameworks such as GDPR and HIPAA is indispensable. VFL facilitates a collaborative approach among institutions, enabling the prediction of disease risks without collecting sensitive patient data. However, VFL remains susceptible to label inference attacks, wherein malicious entities may extrapolate personal data from the exchanged intermediate results. To address the above challenge, we propose a strategic mechanism known as the balanced noise\ninjection strategy (BNIS). This strategy is designed to meticulously regulate the introduction of noise, achieving a trade-off between privacy preservation and model accuracy.\n\nMoreover, to bolster our framework, we propose the multi-loss defense strategy (MLDS), an innovative defense explicitly engineered to withstand direct label inference attacks with resilience. Extensive evaluations on four benchmark datasets demonstrate that our approach defenses against passive attacks and yields a significant improvement in accuracy compared to the prevailing FL similar gradient (FLSG) benchmark. Furthermore, MLDS concurrently addresses breaches in label inference and greatly enhances the precision of the model.","manuscriptTitle":"Multi-Level Defense Strategy for Vertical Federated Learning Against Label Inference Attacks","msid":"","msnumber":"","nonDraftVersions":[{"code":1,"date":"2024-08-07 01:33:05","doi":"10.21203/rs.3.rs-4679192/v1","editorialEvents":[{"type":"communityComments","content":0},{"type":"checksComplete","content":"","date":"2024-07-04T08:39:39+00:00","index":"","fulltext":""},{"type":"submitted","content":"Wireless Networks","date":"2024-07-03T09:22:51+00:00","index":"","fulltext":""}],"status":"published","journal":{"display":true,"email":"[email protected]","identity":"wireless-networks","isNatureJournal":false,"hasQc":true,"allowDirectSubmit":false,"externalIdentity":"wine","sideBox":"Learn more about [Wireless Networks](http://link.springer.com/journal/11276)","snPcode":"11276","submissionUrl":"https://submission.nature.com/new-submission/11276/3","title":"Wireless Networks","twitterHandle":"","acdcEnabled":true,"dfaEnabled":true,"editorialSystem":"stoa","reportingPortfolio":"Springer Hybrid","inReviewEnabled":true,"inReviewRevisionsEnabled":false}}],"origin":"","ownerIdentity":"405d8623-5d67-4819-b485-eb676db05b4d","owner":[],"postedDate":"August 7th, 2024","published":true,"recentEditorialEvents":[],"rejectedJournal":[],"revision":"","amendment":"","status":"under-review","subjectAreas":[],"tags":[],"updatedAt":"2024-08-07T01:33:05+00:00","versionOfRecord":[],"versionCreatedAt":"2024-08-07 01:33:05","video":"","vorDoi":"","vorDoiUrl":"","workflowStages":[]},"version":"v1","identity":"rs-4679192","journalConfig":"researchsquare"},"__N_SSP":true},"page":"/article/[identity]/[[...version]]","query":{"redirect":"/article/rs-4679192","identity":"rs-4679192","version":["v1"]},"buildId":"qtupq5eGEP_6zYnWcrvyt","isFallback":false,"isExperimentalCompile":false,"dynamicIds":[84888],"gssp":true,"scriptLoader":[]}