{"paper_id":"376a2ca2-3188-48ca-8d46-cffadf816030","body_text":"Federated Edge AI for Anomaly Detection in Industrial IoT | 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 Federated Edge AI for Anomaly Detection in Industrial IoT Pankaj Bhambri, Jagdeep Singh, Shashi Kant Gupta, Mudassir Khan, and 4 more This is a preprint; it has not been peer reviewed by a journal. https://doi.org/ 10.21203/rs.3.rs-9478897/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 The rapidly increasing number of industrial IoT (IIoT) devices has increased the demand for real-time anomaly detection to ensure operations remain efficient, reliable and secure from cyber threats. However, legacy centralized approaches to on-line detection of anomalies face serious challenges due to high communication overhead, latency, and privacy-related risks as related to distributed, sensitive industrial data that is being generated by IIoT devices. However, Federated Edge AI Technology presents an attractive new paradigm for enabling collaborative model training on each of the IIoT devices in a completely secure manner while preserving the privacy of their data, by training the models directly on the devices at the edge. The purpose of this paper is to provide a comprehensive overview of recent developments in new federated learning frameworks, lightweight model compression techniques, and edge-based detection techniques. Furthermore, we present new unified federationbased approaches for robust on-device anomaly detection in the IIoT. We use case studies in intrusion detection, eavesdropper detection, and predictive maintenance to illustrate the real-life efficacy of federated edge AI to contribute to the security and operational resilience of IIoT security. The findings conclude by demonstrably highlighting that federated learning with edge intelligence presents a scalable, secure, and efficient processing dealing with anomalies and minimizing errors in IIOT systems. Industrial Internet of Things Federated Learning Edge AI Anomaly Detection Privacy-Preserving Decentralized Learning Intrusion Detection Model Compression Cybersecurity 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-9478897\",\"acceptedTermsAndConditions\":true,\"allowDirectSubmit\":true,\"archivedVersions\":[],\"articleType\":\"Research Article\",\"associatedPublications\":[],\"authors\":[{\"id\":630241503,\"identity\":\"e5734dd3-e51c-4633-8eb5-8bd97c38c7fe\",\"order_by\":0,\"name\":\"Pankaj Bhambri\",\"email\":\"data:image/png;base64,iVBORw0KGgoAAAANSUhEUgAAAZAAAAAyAQMAAABI0h/eAAAABlBMVEX///8AAABVwtN+AAAACXBIWXMAAA7EAAAOxAGVKw4bAAABBklEQVRIiWNgGAWjYFCCxAcg0oCB4fDBAwlAFh+Iy4NXS7IBVMuxBLAWNhK08BgcYCBGizl7MgNzQc0dY/7GMx8OPNxhJ8cm3cD44G0bQzTEBExg2fOYgXnGsWdmEgfObjiQeCbZmE3mALPh3DaG3A04tBjcyD/AzMN22IYBrKUNiCQS2KR58WoBOozn32Eb+QNnHsC0sP8mqIW37bCZwYEzDHBbmPFpAfnl8My+w8aGB44ZANUD/SKR2Cw555xE7kwcWoAhxvi44Nthw3k3Dj98+LPNTo5fIvnghzdlNrl9uBwGxIfBLAm4CsYGEJdBAY8WZjCLvwFNSh5dYBSMglEwCkYqAAA5aGcaUnCdjQAAAABJRU5ErkJggg==\",\"orcid\":\"\",\"institution\":\"Lincoln University College\",\"correspondingAuthor\":true,\"prefix\":\"\",\"firstName\":\"Pankaj\",\"middleName\":\"\",\"lastName\":\"Bhambri\",\"suffix\":\"\"},{\"id\":630241504,\"identity\":\"171c88c4-210b-4d13-aa34-27e4b0097b5d\",\"order_by\":1,\"name\":\"Jagdeep Singh\",\"email\":\"\",\"orcid\":\"\",\"institution\":\"Guru Nanak Dev Engineering College\",\"correspondingAuthor\":false,\"prefix\":\"\",\"firstName\":\"Jagdeep\",\"middleName\":\"\",\"lastName\":\"Singh\",\"suffix\":\"\"},{\"id\":630241505,\"identity\":\"475546de-c7ab-43ec-a6b6-54c8e94228c9\",\"order_by\":2,\"name\":\"Shashi Kant Gupta\",\"email\":\"\",\"orcid\":\"\",\"institution\":\"Lincoln University College\",\"correspondingAuthor\":false,\"prefix\":\"\",\"firstName\":\"Shashi\",\"middleName\":\"Kant\",\"lastName\":\"Gupta\",\"suffix\":\"\"},{\"id\":630241506,\"identity\":\"deb7ca99-d8ed-4463-89db-7c1d30a558be\",\"order_by\":3,\"name\":\"Mudassir Khan\",\"email\":\"\",\"orcid\":\"\",\"institution\":\"King Khalid University\",\"correspondingAuthor\":false,\"prefix\":\"\",\"firstName\":\"Mudassir\",\"middleName\":\"\",\"lastName\":\"Khan\",\"suffix\":\"\"},{\"id\":630241507,\"identity\":\"be792aa5-8446-43ba-8085-19e7b0ae8581\",\"order_by\":4,\"name\":\"Amina Salhi\",\"email\":\"\",\"orcid\":\"\",\"institution\":\"Princess Nourah bint Abdulrahman University\",\"correspondingAuthor\":false,\"prefix\":\"\",\"firstName\":\"Amina\",\"middleName\":\"\",\"lastName\":\"Salhi\",\"suffix\":\"\"},{\"id\":630241508,\"identity\":\"9ec4800f-98d4-4156-9b71-b94c1ab8062a\",\"order_by\":5,\"name\":\"Mohammed Inamur Rahman\",\"email\":\"\",\"orcid\":\"\",\"institution\":\"King Khalid University\",\"correspondingAuthor\":false,\"prefix\":\"\",\"firstName\":\"Mohammed\",\"middleName\":\"Inamur\",\"lastName\":\"Rahman\",\"suffix\":\"\"},{\"id\":630241509,\"identity\":\"3495de1b-6a82-4373-bf62-840d2d9be575\",\"order_by\":6,\"name\":\"Mehardeep Kaur\",\"email\":\"\",\"orcid\":\"\",\"institution\":\"Guru Nanak Dev Engineering College\",\"correspondingAuthor\":false,\"prefix\":\"\",\"firstName\":\"Mehardeep\",\"middleName\":\"\",\"lastName\":\"Kaur\",\"suffix\":\"\"},{\"id\":630241510,\"identity\":\"af7d478d-36e9-4ede-a0d8-b5ccac73c162\",\"order_by\":7,\"name\":\"Kiran Rani\",\"email\":\"\",\"orcid\":\"\",\"institution\":\"Guru Nanak Dev Engineering College\",\"correspondingAuthor\":false,\"prefix\":\"\",\"firstName\":\"Kiran\",\"middleName\":\"\",\"lastName\":\"Rani\",\"suffix\":\"\"}],\"badges\":[],\"createdAt\":\"2026-04-21 05:10:21\",\"currentVersionCode\":1,\"declarations\":\"\",\"doi\":\"10.21203/rs.3.rs-9478897/v1\",\"doiUrl\":\"https://doi.org/10.21203/rs.3.rs-9478897/v1\",\"draftVersion\":[],\"editorialEvents\":[],\"editorialNote\":\"\",\"failedWorkflow\":false,\"files\":[{\"id\":109195712,\"identity\":\"4d32015a-305a-4c19-b821-f64b435122d5\",\"added_by\":\"auto\",\"created_at\":\"2026-05-13 12:59:20\",\"extension\":\"pdf\",\"order_by\":1,\"title\":\"\",\"display\":\"\",\"copyAsset\":false,\"role\":\"manuscript-pdf\",\"size\":528289,\"visible\":true,\"origin\":\"\",\"legend\":\"\",\"description\":\"\",\"filename\":\"FederatedEdgeAIforAnomalyDetectioninIndustrialIoTUpdated.pdf\",\"url\":\"https://assets-eu.researchsquare.com/files/rs-9478897/v1_covered_375c02e6-014a-4ba2-9afc-3f33b2abd5e6.pdf\"}],\"financialInterests\":\"No competing interests reported.\",\"formattedTitle\":\"Federated Edge AI for Anomaly Detection in Industrial IoT\",\"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\":\"info@researchsquare.com\",\"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\":\"Industrial Internet of Things, Federated Learning, Edge AI, Anomaly Detection, Privacy-Preserving, Decentralized Learning, Intrusion Detection, Model Compression, Cybersecurity \",\"lastPublishedDoi\":\"10.21203/rs.3.rs-9478897/v1\",\"lastPublishedDoiUrl\":\"https://doi.org/10.21203/rs.3.rs-9478897/v1\",\"license\":{\"name\":\"CC BY 4.0\",\"url\":\"https://creativecommons.org/licenses/by/4.0/\"},\"manuscriptAbstract\":\"The rapidly increasing number of industrial IoT (IIoT) devices has increased the demand for real-time anomaly detection to ensure operations remain efficient, reliable and secure from cyber threats. However, legacy centralized approaches to on-line detection of anomalies face serious challenges due to high communication overhead, latency, and privacy-related risks as related to distributed, sensitive industrial data that is being generated by IIoT devices. However, Federated Edge AI Technology presents an attractive new paradigm for enabling collaborative model training on each of the IIoT devices in a completely secure manner while preserving the privacy of their data, by training the models directly on the devices at the edge. The purpose of this paper is to provide a comprehensive overview of recent developments in new federated learning frameworks, lightweight model compression techniques, and edge-based detection techniques. Furthermore, we present new unified federationbased approaches for robust on-device anomaly detection in the IIoT. We use case studies in intrusion detection, eavesdropper detection, and predictive maintenance to illustrate the real-life efficacy of federated edge AI to contribute to the security and operational resilience of IIoT security. The findings conclude by demonstrably highlighting that federated learning with edge intelligence presents a scalable, secure, and efficient processing dealing with anomalies and minimizing errors in IIOT systems.\",\"manuscriptTitle\":\"Federated Edge AI for Anomaly Detection in Industrial IoT\",\"msid\":\"\",\"msnumber\":\"\",\"nonDraftVersions\":[{\"code\":1,\"date\":\"2026-04-27 15:27:25\",\"doi\":\"10.21203/rs.3.rs-9478897/v1\",\"editorialEvents\":[{\"type\":\"communityComments\",\"content\":0}],\"status\":\"published\",\"journal\":{\"display\":true,\"email\":\"info@researchsquare.com\",\"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\":\"4a42d4ab-423d-4e3b-8bf8-39766274cfe6\",\"owner\":[],\"postedDate\":\"April 27th, 2026\",\"published\":true,\"recentEditorialEvents\":[{\"type\":\"decision\",\"content\":\"Rejected\",\"date\":\"2026-05-13T12:38:51+00:00\",\"index\":\"\",\"fulltext\":\"\"},{\"type\":\"editorInvitedReview\",\"content\":\"\",\"date\":\"2026-05-13T06:26:20+00:00\",\"index\":29,\"fulltext\":\"\"},{\"type\":\"reviewerAgreed\",\"content\":\"280633100141255069592229929528143612139\",\"date\":\"2026-04-29T03:46:52+00:00\",\"index\":25,\"fulltext\":\"\"}],\"rejectedJournal\":[],\"revision\":\"\",\"amendment\":\"\",\"status\":\"posted\",\"subjectAreas\":[],\"tags\":[],\"updatedAt\":\"2026-05-13T12:57:39+00:00\",\"versionOfRecord\":[],\"versionCreatedAt\":\"2026-04-27 15:27:25\",\"video\":\"\",\"vorDoi\":\"\",\"vorDoiUrl\":\"\",\"workflowStages\":[]},\"version\":\"v1\",\"identity\":\"rs-9478897\",\"journalConfig\":\"researchsquare\"},\"__N_SSP\":true},\"page\":\"/article/[identity]/[[...version]]\",\"query\":{\"redirect\":\"/article/rs-9478897\",\"identity\":\"rs-9478897\",\"version\":[\"v1\"]},\"buildId\":\"XKTyCvWXoU3ODBz1xrDgd\",\"isFallback\":false,\"isExperimentalCompile\":false,\"dynamicIds\":[84888],\"gssp\":true,\"scriptLoader\":[]}","source_license":"CC-BY-4.0","license_restricted":false}