G-SAFE: Generative Synthetic Augmentation for Federated Edge Security

G-SAFE: Generative Synthetic Augmentation for Federated Edge Security | 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 G-SAFE: Generative Synthetic Augmentation for Federated Edge Security Tutan Ghosh¹, Ira Nath² This is a preprint; it has not been peer reviewed by a journal. https://doi.org/ 10.21203/rs.3.rs-7447294/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) has emerged as a promising decentralized machine learning paradigm for edge computing, enabling collaborative model training without sharing raw data. However, FL models can suffer from limited and non-iid local datasets and lingering privacy risks from model updates. In this paper, we introduce G-SAFE (Generative Synthetic Augmentation for Federated Edge Security) , a novel framework that integrates generative artificial intelligence (AI) with federated learning to enhance security applications at the network edge. G-SAFE leverages generative models (such as GANs) at each client to produce synthetic data that augment local training sets, thereby improving model generalization and addressing data scarcity and imbalance. The synthetic samples preserve statistical characteristics of sensitive data without exposing personal identifiers, mitigating privacy concerns. We design a two-fold methodology comprising a client-side generative augmentation strategy and a privacy-preserving federated training process . The augmented local models are periodically aggregated by the server, yielding a robust global model. We evaluate G-SAFE on a distributed intrusion detection use-case with IoT edge devices. Results show that our approach accelerates model convergence and significantly improves detection performance over standard FL. G-SAFE achieves a global accuracy of ~98.3%, approaching the centralized training upper bound (≈99%), and outperforms vanilla federated learning by over 2.5% absolute accuracy. Precision–recall metrics for minority attack classes substantially improve (e.g. recall +35% for rare exploits) with synthetic augmentation. We compare G-SAFE against baseline methods and discuss its impact on privacy, showing that sharing only generative models or synthetic data further reduces information leakage risks. This work demonstrates that generative synthetic augmentation can greatly enhance federated edge security systems by balancing data utility and privacy. Federated Learning Generative Adversarial Networks Synthetic Data Edge Security Privacy Preservation Intrusion Detection Internet of Things (IoT) Security Distributed Machine Learning Data Augmentation Deep 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-7447294","acceptedTermsAndConditions":true,"allowDirectSubmit":true,"archivedVersions":[],"articleType":"Research Article","associatedPublications":[],"authors":[{"id":518917499,"identity":"fa9393a9-869d-4388-b106-8b93499b3dee","order_by":0,"name":"Tutan Ghosh¹","email":"data:image/png;base64,iVBORw0KGgoAAAANSUhEUgAAAZAAAAAyAQMAAABI0h/eAAAABlBMVEX///8AAABVwtN+AAAACXBIWXMAAA7EAAAOxAGVKw4bAAABCklEQVRIiWNgGAWjYNCCigNwpgwfjMWGQzEPAzOQPAPVAqR44CrxamFsw6YFF7CXyD/4uXDeHXnz9uMPP3+oseFhY2+/+IChxo6BT7oBuy0SyczSM7c9M5xzJsdY4sCxNB42njPFBgzHkhnYZA7g0sIgzbvtMOMMhhwGiYMNh3nYJHLSJBjYDjCwSSTgtOU375zD9jP4nz/+AdYi/yb9B8M/vFrYpHkbDifOkEgwg9rCfgwcIDi1nHlsZs1z7FnyDIk3ZhZnwH7JYZZI7EvmwaWFvT3x8W2emju2M/jTH9+oqLGR42c//vDDh292cvIzsGvBarMBQwIoxkgA7A9IUT0KRsEoGAXDHwAAMVdWHV1hU5sAAAAASUVORK5CYII=","orcid":"","institution":"Barasat College","correspondingAuthor":true,"prefix":"","firstName":"Tutan","middleName":"","lastName":"Ghosh¹","suffix":""},{"id":518917500,"identity":"adc82114-d774-4c24-a813-1cf12977acbb","order_by":1,"name":"Ira Nath²","email":"","orcid":"","institution":"JIS College of Engineering","correspondingAuthor":false,"prefix":"","firstName":"Ira","middleName":"","lastName":"Nath²","suffix":""}],"badges":[],"createdAt":"2025-08-24 16:08:06","currentVersionCode":1,"declarations":"","doi":"10.21203/rs.3.rs-7447294/v1","doiUrl":"https://doi.org/10.21203/rs.3.rs-7447294/v1","draftVersion":[],"editorialEvents":[],"editorialNote":"","failedWorkflow":false,"files":[{"id":92112203,"identity":"4df2fcaf-a6f8-48af-ba85-795022bb0c90","added_by":"auto","created_at":"2025-09-24 18:45:15","extension":"docx","order_by":0,"title":"","display":"","copyAsset":false,"role":"acdc-reference","size":2045168,"visible":true,"origin":"","legend":"","description":"","filename":"GSAFE.docx","url":"https://assets-eu.researchsquare.com/files/rs-7447294/v1/def3f79606fce5414ab4e2c6.docx"},{"id":92111707,"identity":"34de5023-b7a7-4c29-b54d-eae0f95bb576","added_by":"auto","created_at":"2025-09-24 18:37:14","extension":"json","order_by":1,"title":"","display":"","copyAsset":false,"role":"acdc-reference","size":4598,"visible":true,"origin":"","legend":"","description":"","filename":"c8d5a4e73ba84638a5e8c2410308edf7.json","url":"https://assets-eu.researchsquare.com/files/rs-7447294/v1/b43c2eaf550d9299edbfd177.json"},{"id":92113013,"identity":"8937b373-ac97-4a04-bb39-9dcd969e176b","added_by":"auto","created_at":"2025-09-24 18:53:15","extension":"xml","order_by":2,"title":"","display":"","copyAsset":false,"role":"acdc-reference","size":97458,"visible":true,"origin":"","legend":"","description":"","filename":"c8d5a4e73ba84638a5e8c2410308edf71enriched.xml","url":"https://assets-eu.researchsquare.com/files/rs-7447294/v1/e8a027a2927855d332d733fe.xml"},{"id":92111708,"identity":"333b2677-d270-4cde-bd30-7540361647f9","added_by":"auto","created_at":"2025-09-24 18:37:15","extension":"png","order_by":6,"title":"","display":"","copyAsset":false,"role":"acdc-reference","size":52405,"visible":true,"origin":"","legend":"","description":"","filename":"Onlinefloatimage1.png","url":"https://assets-eu.researchsquare.com/files/rs-7447294/v1/6cd1a7c251b5ce566238ee7e.png"},{"id":92111711,"identity":"34d7d60d-54b5-40c6-92d3-07a4ecf59e57","added_by":"auto","created_at":"2025-09-24 18:37:15","extension":"png","order_by":7,"title":"","display":"","copyAsset":false,"role":"acdc-reference","size":17102,"visible":true,"origin":"","legend":"","description":"","filename":"Onlinefloatimage2.png","url":"https://assets-eu.researchsquare.com/files/rs-7447294/v1/52a0a494bbe71eb77934eaa9.png"},{"id":92111713,"identity":"a3637629-1794-4226-9aaa-df1876d32827","added_by":"auto","created_at":"2025-09-24 18:37:15","extension":"xml","order_by":8,"title":"","display":"","copyAsset":false,"role":"acdc-reference","size":95698,"visible":true,"origin":"","legend":"","description":"","filename":"c8d5a4e73ba84638a5e8c2410308edf71structuring.xml","url":"https://assets-eu.researchsquare.com/files/rs-7447294/v1/624906490314a8e34fdc0417.xml"},{"id":92111712,"identity":"be11441d-1088-4e66-af5d-0acf2f64e457","added_by":"auto","created_at":"2025-09-24 18:37:15","extension":"html","order_by":9,"title":"","display":"","copyAsset":false,"role":"acdc-reference","size":106199,"visible":true,"origin":"","legend":"","description":"","filename":"earlyproof.html","url":"https://assets-eu.researchsquare.com/files/rs-7447294/v1/1102a49c8bce9c8684599940.html"},{"id":104782228,"identity":"113e1efa-7c5f-4e59-952d-af57d4733285","added_by":"auto","created_at":"2026-03-17 07:57:00","extension":"pdf","order_by":1,"title":"","display":"","copyAsset":false,"role":"manuscript-pdf","size":537443,"visible":true,"origin":"","legend":"","description":"","filename":"GSAFE.pdf","url":"https://assets-eu.researchsquare.com/files/rs-7447294/v1_covered_e1e5cd87-777f-464e-9e11-5045bb52a5f4.pdf"}],"financialInterests":"No competing interests reported.","formattedTitle":"G-SAFE: Generative Synthetic Augmentation for Federated Edge Security","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, Generative Adversarial Networks, Synthetic Data, Edge Security, Privacy Preservation, Intrusion Detection, Internet of Things (IoT) Security, Distributed Machine Learning, Data Augmentation, Deep Learning","lastPublishedDoi":"10.21203/rs.3.rs-7447294/v1","lastPublishedDoiUrl":"https://doi.org/10.21203/rs.3.rs-7447294/v1","license":{"name":"CC BY 4.0","url":"https://creativecommons.org/licenses/by/4.0/"},"manuscriptAbstract":"\u003cp\u003eFederated learning (FL) has emerged as a promising decentralized machine learning paradigm for edge computing, enabling collaborative model training without sharing raw data. However, FL models can suffer from limited and non-iid local datasets and lingering privacy risks from model updates. In this paper, we introduce \u003cstrong\u003eG-SAFE (Generative Synthetic Augmentation for Federated Edge Security)\u003c/strong\u003e, a novel framework that integrates generative artificial intelligence (AI) with federated learning to enhance security applications at the network edge. G-SAFE leverages generative models (such as GANs) at each client to produce \u003cem\u003esynthetic data\u003c/em\u003e that augment local training sets, thereby improving model generalization and addressing data scarcity and imbalance. The synthetic samples preserve statistical characteristics of sensitive data without exposing personal identifiers, mitigating privacy concerns. We design a two-fold methodology comprising a \u003cem\u003eclient-side generative augmentation strategy\u003c/em\u003eand a \u003cem\u003eprivacy-preserving federated training process\u003c/em\u003e. The augmented local models are periodically aggregated by the server, yielding a robust global model. We evaluate G-SAFE on a distributed intrusion detection use-case with IoT edge devices. \u003cstrong\u003eResults\u003c/strong\u003e show that our approach accelerates model convergence and significantly improves detection performance over standard FL. G-SAFE achieves a global accuracy of ~98.3%, approaching the centralized training upper bound (≈99%), and outperforms vanilla federated learning by over 2.5% absolute accuracy. Precision–recall metrics for minority attack classes substantially improve (e.g. recall +35% for rare exploits) with synthetic augmentation. We compare G-SAFE against baseline methods and discuss its impact on privacy, showing that sharing only generative models or synthetic data further reduces information leakage risks. This work demonstrates that generative synthetic augmentation can greatly enhance federated edge security systems by balancing data utility and privacy.\u003c/p\u003e","manuscriptTitle":"G-SAFE: Generative Synthetic Augmentation for Federated Edge Security","msid":"","msnumber":"","nonDraftVersions":[{"code":1,"date":"2025-09-24 18:37:10","doi":"10.21203/rs.3.rs-7447294/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":"72c2d4d6-2080-4ae0-a83f-b5e7f99eb7a4","owner":[],"postedDate":"September 24th, 2025","published":true,"recentEditorialEvents":[],"rejectedJournal":[],"revision":"","amendment":"","status":"posted","subjectAreas":[],"tags":[],"updatedAt":"2026-03-15T12:09:31+00:00","versionOfRecord":[],"versionCreatedAt":"2025-09-24 18:37:10","video":"","vorDoi":"","vorDoiUrl":"","workflowStages":[]},"version":"v1","identity":"rs-7447294","journalConfig":"researchsquare"},"__N_SSP":true},"page":"/article/[identity]/[[...version]]","query":{"redirect":"/article/rs-7447294","identity":"rs-7447294","version":["v1"]},"buildId":"8U1c8b4HqxoKbykW_rLl7","isFallback":false,"isExperimentalCompile":false,"dynamicIds":[84888],"gssp":true,"scriptLoader":[]}