A Bijection-backdoor-based Adversarial Examples Defense Method in Federated Learning

A Bijection-backdoor-based Adversarial Examples Defense Method 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 A Bijection-backdoor-based Adversarial Examples Defense Method in Federated Learning Yongfei Li, Yuanbo Guo, Chen Fang, Yifeng Wang, Qingli Chen, Yongjin Hu This is a preprint; it has not been peer reviewed by a journal. https://doi.org/ 10.21203/rs.3.rs-4718612/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 With the continuous advancement of Internet of Things (IoT), the issue of data privacy in it is also quietly emerging. Federated learning (FL) enables the creation of a potent global model from a consortium of clients, safeguarding sensitive client data while upholding model accuracy. Unlike conventional centralized learning paradigms, federated learning operates without necessitating access to local datasets, thus effectively mitigating data privacy concerns. Nonetheless, malevolent entities can exploit vulnerabilities by introducing subtle perturbations to client-side samples, thereby executing adversarial example (AE) attacks that disrupt model predictions. To address this challenge, we present a novel bijection-backdoor-based adversarial examples defense method in federated learning, termed BAEDFL-CL. Initially, an intricate backdoor mechanism is transmitted from the server to the client, i.e. IoT device, neutralizing the impact of adversarial examples on model outputs while preserving the primary task's performance. Additionally, to bolster the model's defense capabilities within the federated learning for practical scenario, we devise a representation enhancement technique grounded in supervised contrastive learning (CL). This method encourages the model to craft feature representations endowed with enhanced generalization ability. Through comprehensive experiment on diverse datasets spanning IID and Non-IID scenarios, our results reveal that BAEDFL-CL significantly diminishes the attack success rate to 17.66% and 24.35%, respectively. Concurrently, BAEDFL-CL improves main task performance by 0.02% and 2.24% correspondingly, substantiating its efficacy in countering adversarial examples in federated learning environments. Federated learning Internet of things Adversarial example Bijection backdoor Contrastive learning Full Text Additional Declarations No competing interests reported. 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-4718612","acceptedTermsAndConditions":true,"allowDirectSubmit":true,"archivedVersions":[],"articleType":"Research Article","associatedPublications":[],"authors":[{"id":329125529,"identity":"4b2eb9be-debc-42cf-8988-ab1679e6e36b","order_by":0,"name":"Yongfei Li","email":"","orcid":"","institution":"Information Engineering University","correspondingAuthor":false,"prefix":"","firstName":"Yongfei","middleName":"","lastName":"Li","suffix":""},{"id":329125531,"identity":"09a3ba13-8685-499a-9eb6-706c47ea926c","order_by":1,"name":"Yuanbo Guo","email":"","orcid":"","institution":"Hainan University","correspondingAuthor":false,"prefix":"","firstName":"Yuanbo","middleName":"","lastName":"Guo","suffix":""},{"id":329125532,"identity":"8fb2d2e3-46d4-49de-a5c4-4fe26ee89285","order_by":2,"name":"Chen Fang","email":"data:image/png;base64,iVBORw0KGgoAAAANSUhEUgAAAZAAAAAyAQMAAABI0h/eAAAABlBMVEX///8AAABVwtN+AAAACXBIWXMAAA7EAAAOxAGVKw4bAAAA6klEQVRIie3RMWvCQBTA8RdOXhEeZj2JJF8hItznuUPoZMGpZMgQUXRQ9/sYmWy7KYXrct0dU/wA1alOYjq3JHFzuN98f7j3HoDj3CGMvn+OxyQl/2G6K2SS1icdkMLT1oTdlRnGhTX1SVgmrD1ng1iPRPdrxhp8DLaPB0BUOYxEojIEf7GU1YmXfQzG1FMvYJ736rUH3H7m1QnzskBzVG+T6WavLELMn2oSZBBQzFT+DmKs5qxBQogByXJ80xLQLOHE+nr7u2QccmkN1c4SafKK06U8ZXTYnc5JGvqLdXXyB9323HEcx/nXFZBWR9iYSgeSAAAAAElFTkSuQmCC","orcid":"","institution":"Information Engineering University","correspondingAuthor":true,"prefix":"","firstName":"Chen","middleName":"","lastName":"Fang","suffix":""},{"id":329125533,"identity":"ed728929-934d-4eb2-bc68-3c8b8bbe55e1","order_by":3,"name":"Yifeng Wang","email":"","orcid":"","institution":"Hainan University","correspondingAuthor":false,"prefix":"","firstName":"Yifeng","middleName":"","lastName":"Wang","suffix":""},{"id":329125534,"identity":"0631a034-d0ce-4818-98ef-11b5ec27fcec","order_by":4,"name":"Qingli Chen","email":"","orcid":"","institution":"Information Engineering University","correspondingAuthor":false,"prefix":"","firstName":"Qingli","middleName":"","lastName":"Chen","suffix":""},{"id":329125535,"identity":"0ec0186a-3305-44fc-88ad-4fead37b376e","order_by":5,"name":"Yongjin Hu","email":"","orcid":"","institution":"Information Engineering University","correspondingAuthor":false,"prefix":"","firstName":"Yongjin","middleName":"","lastName":"Hu","suffix":""}],"badges":[],"createdAt":"2024-07-10 14:23:45","currentVersionCode":1,"declarations":"","doi":"10.21203/rs.3.rs-4718612/v1","doiUrl":"https://doi.org/10.21203/rs.3.rs-4718612/v1","draftVersion":[],"editorialEvents":[],"editorialNote":"","failedWorkflow":false,"files":[{"id":65002290,"identity":"de6fccce-d3f2-495a-b5ad-26b4d3f54d65","added_by":"auto","created_at":"2024-09-22 01:44:24","extension":"pdf","order_by":1,"title":"","display":"","copyAsset":false,"role":"manuscript-pdf","size":10033555,"visible":true,"origin":"","legend":"","description":"","filename":"Springer.pdf","url":"https://assets-eu.researchsquare.com/files/rs-4718612/v1_covered_637d9418-842d-46cf-9ed6-963b0753a486.pdf"}],"financialInterests":"No competing interests reported.","formattedTitle":"A Bijection-backdoor-based Adversarial Examples Defense Method in Federated Learning","fulltext":[],"fulltextSource":"","fullText":"","funders":[],"hasAdminPriorityOnWorkflow":false,"hasManuscriptDocX":false,"hasOptedInToPreprint":true,"hasPassedJournalQc":"","hasAnyPriority":false,"hideJournal":true,"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":"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":"Federated learning, Internet of things, Adversarial example, Bijection backdoor, Contrastive learning","lastPublishedDoi":"10.21203/rs.3.rs-4718612/v1","lastPublishedDoiUrl":"https://doi.org/10.21203/rs.3.rs-4718612/v1","license":{"name":"CC BY 4.0","url":"https://creativecommons.org/licenses/by/4.0/"},"manuscriptAbstract":"With the continuous advancement of Internet of Things (IoT), the issue of data privacy in it is also quietly emerging. Federated learning (FL) enables the creation of a potent global model from a consortium of clients, safeguarding sensitive client data while upholding model accuracy. Unlike conventional centralized learning paradigms, federated learning operates without necessitating access to local datasets, thus effectively mitigating data privacy concerns. Nonetheless, malevolent entities can exploit vulnerabilities by introducing subtle perturbations to client-side samples, thereby executing adversarial example (AE) attacks that disrupt model predictions. To address this challenge, we present a novel bijection-backdoor-based adversarial examples defense method in federated learning, termed BAEDFL-CL. Initially, an intricate backdoor mechanism is transmitted from the server to the client, i.e. IoT device, neutralizing the impact of adversarial examples on model outputs while preserving the primary task's performance. Additionally, to bolster the model's defense capabilities within the federated learning for practical scenario, we devise a representation enhancement technique grounded in supervised contrastive learning (CL). This method encourages the model to craft feature representations endowed with enhanced generalization ability. Through comprehensive experiment on diverse datasets spanning IID and Non-IID scenarios, our results reveal that BAEDFL-CL significantly diminishes the attack success rate to 17.66% and 24.35%, respectively. Concurrently, BAEDFL-CL improves main task performance by 0.02% and 2.24% correspondingly, substantiating its efficacy in countering adversarial examples in federated learning environments.","manuscriptTitle":"A Bijection-backdoor-based Adversarial Examples Defense Method in Federated Learning","msid":"","msnumber":"","nonDraftVersions":[{"code":1,"date":"2024-08-05 05:42:54","doi":"10.21203/rs.3.rs-4718612/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":"0e43b7ea-3f21-4999-a1b2-6d53eb3ec1d7","owner":[],"postedDate":"August 5th, 2024","published":true,"recentEditorialEvents":[],"rejectedJournal":[],"revision":"","amendment":"","status":"posted","subjectAreas":[],"tags":[],"updatedAt":"2024-09-22T01:36:16+00:00","versionOfRecord":[],"versionCreatedAt":"2024-08-05 05:42:54","video":"","vorDoi":"","vorDoiUrl":"","workflowStages":[]},"version":"v1","identity":"rs-4718612","journalConfig":"researchsquare"},"__N_SSP":true},"page":"/article/[identity]/[[...version]]","query":{"redirect":"/article/rs-4718612","identity":"rs-4718612","version":["v1"]},"buildId":"qtupq5eGEP_6zYnWcrvyt","isFallback":false,"isExperimentalCompile":false,"dynamicIds":[84888],"gssp":true,"scriptLoader":[]}