Governance-Aware Federated Learning for Trustworthy and Compliant Decentralized Infrastructure Monitoring

Governance-Aware Federated Learning for Trustworthy and Compliant Decentralized Infrastructure Monitoring | 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 Governance-Aware Federated Learning for Trustworthy and Compliant Decentralized Infrastructure Monitoring Seyed Amirhossein Mousaviniya Qasemabadi, Mohammadmahdi Rezaeifar Sangchouli, and 1 more This is a preprint; it has not been peer reviewed by a journal. https://doi.org/ 10.21203/rs.3.rs-9138351/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 paper introduces a federated learning (GFL) architecture that is governed to monitor decentralized infrastructure in a legally heterogeneous setting. The framework incorporates legal compliance limits, auditability controls, and policy alignment as governed by LLM into the federated optimization process, thus creating the possibility of trustful and policy-oriented deployment of AI to the nodes of the public sector.This is to develop a mathematical model that embodies multi-agent lawful infestations, metadata audit rating, and also dynamic trust stabilization within the limits of regulations. Empirical analysis with a synthesized dataset of 20 European jurisdiction nodes reveals that the GFL model performs better than governance-free baselines in the accuracy of their predictions +1 3.5 %) and concurrently enhances transparency, explainability, and auditability. Clients that follow a legal and semantic protocol of governance always provide quality and more consistent updates. The findings show that rather than deterring model convergence and trust in the decentralized systems, the enforcement of governance improves such aspects. The paper is another addition to the intersection of federated AI in digital governance, providing a scalable strategy to institutional compliance in critical areas of infrastructure, such as smart grids, urban mobility, and environmental sensing Theoretical Computer Science Computer Architecture and Engineering Federated Learning Governance-aware AI Legal Compliance Public Infrastructure Monitoring Transparency and Auditability LLM-guided Policy Alignment Full Text Additional Declarations The authors declare no competing interests. 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-9138351","acceptedTermsAndConditions":true,"allowDirectSubmit":true,"archivedVersions":[],"articleType":"Research Article","associatedPublications":[],"authors":[{"id":606960358,"identity":"e0d9a2d4-f868-4b97-a1a5-432500dd14bd","order_by":0,"name":"Seyed Amirhossein Mousaviniya Qasemabadi","email":"data:image/png;base64,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","orcid":"","institution":"Department of Computer Engineering, Islamic Azad University, Bojnord Branch, Bojnord, Iran","correspondingAuthor":true,"prefix":"","firstName":"Seyed","middleName":"Amirhossein Mousaviniya","lastName":"Qasemabadi","suffix":""},{"id":606960359,"identity":"5eb5442a-9669-4988-8703-58f654b41ba7","order_by":1,"name":"Mohammadmahdi Rezaeifar Sangchouli","email":"","orcid":"","institution":"Faculty of Engineering, Islamic Azad University, Torbat-e Jam Branch, Torbat-e Jam, Iran","correspondingAuthor":false,"prefix":"","firstName":"Mohammadmahdi","middleName":"Rezaeifar","lastName":"Sangchouli","suffix":""},{"id":606960360,"identity":"dd44869d-fe8c-4d9e-856b-6edaf68bf61a","order_by":2,"name":"Fatemeh Zahra HosseiniMoghadam Shadman","email":"","orcid":"","institution":"Department of Information Technology, Payame Noor University, Gonabad Center, Gonabad, Iran","correspondingAuthor":false,"prefix":"","firstName":"Fatemeh","middleName":"Zahra HosseiniMoghadam","lastName":"Shadman","suffix":""}],"badges":[],"createdAt":"2026-03-16 13:18:05","currentVersionCode":1,"declarations":{"humanSubjects":false,"vertebrateSubjects":false,"conflictsOfInterestStatement":false,"humanSubjectEthicalGuidelines":false,"humanSubjectConsent":false,"humanSubjectClinicalTrial":false,"humanSubjectCaseReport":false,"vertebrateSubjectEthicalGuidelines":false},"doi":"10.21203/rs.3.rs-9138351/v1","doiUrl":"https://doi.org/10.21203/rs.3.rs-9138351/v1","draftVersion":[],"editorialEvents":[],"editorialNote":"","failedWorkflow":false,"files":[{"id":104783410,"identity":"7aca7c11-d4fb-42b5-8154-f3b8c41ab57d","added_by":"auto","created_at":"2026-03-17 07:58:52","extension":"pdf","order_by":1,"title":"","display":"","copyAsset":false,"role":"manuscript-pdf","size":431716,"visible":true,"origin":"","legend":"","description":"","filename":"FederatedLearningArchitecturesforDecentralizedInfrastructureMonitoringwithGovernanceConstraints5.pdf","url":"https://assets-eu.researchsquare.com/files/rs-9138351/v1_covered_0f531968-dbf9-492e-83a8-aeb1d1bf9d43.pdf"}],"financialInterests":"The authors declare no competing interests.","formattedTitle":"\u003cp\u003eGovernance-Aware Federated Learning for Trustworthy and Compliant Decentralized Infrastructure Monitoring\u003c/p\u003e","fulltext":[],"fulltextSource":"","fullText":"","funders":[],"hasAdminPriorityOnWorkflow":false,"hasManuscriptDocX":false,"hasOptedInToPreprint":true,"hasPassedJournalQc":"","hasAnyPriority":true,"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,Governance-aware AI ,Legal Compliance,Public Infrastructure Monitoring,Transparency and Auditability,LLM-guided Policy Alignment","lastPublishedDoi":"10.21203/rs.3.rs-9138351/v1","lastPublishedDoiUrl":"https://doi.org/10.21203/rs.3.rs-9138351/v1","license":{"name":"CC BY 4.0","url":"https://creativecommons.org/licenses/by/4.0/"},"manuscriptAbstract":"\u003cp\u003eThe paper introduces a federated learning (GFL) architecture that is governed to monitor decentralized infrastructure in a legally heterogeneous setting. The framework incorporates legal compliance limits, auditability controls, and policy alignment as governed by LLM into the federated optimization process, thus creating the possibility of trustful and policy-oriented deployment of AI to the nodes of the public sector.This is to develop a mathematical model that embodies multi-agent lawful infestations, metadata audit rating, and also dynamic trust stabilization within the limits of regulations. Empirical analysis with a synthesized dataset of 20 European jurisdiction nodes reveals that the GFL model performs better than governance-free baselines in the accuracy of their predictions +1 3.5 %) and concurrently enhances transparency, explainability, and auditability. Clients that follow a legal and semantic protocol of governance always provide quality and more consistent updates. The findings show that rather than deterring model convergence and trust in the decentralized systems, the enforcement of governance improves such aspects. The paper is another addition to the intersection of federated AI in digital governance, providing a scalable strategy to institutional compliance in critical areas of infrastructure, such as smart grids, urban mobility, and environmental sensing\u003c/p\u003e","manuscriptTitle":"Governance-Aware Federated Learning for Trustworthy and Compliant Decentralized Infrastructure Monitoring","msid":"","msnumber":"","nonDraftVersions":[{"code":1,"date":"2026-03-17 03:28:56","doi":"10.21203/rs.3.rs-9138351/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":"6f909dbb-6784-4750-b2ad-22ff5d0e4859","owner":[],"postedDate":"March 17th, 2026","published":true,"recentEditorialEvents":[],"rejectedJournal":[],"revision":"","amendment":"","status":"posted","subjectAreas":[{"id":64585723,"name":"Theoretical Computer Science"},{"id":64585724,"name":"Computer Architecture and Engineering"}],"tags":[],"updatedAt":"2026-03-17T03:28:56+00:00","versionOfRecord":[],"versionCreatedAt":"2026-03-17 03:28:56","video":"","vorDoi":"","vorDoiUrl":"","workflowStages":[]},"version":"v1","identity":"rs-9138351","journalConfig":"researchsquare"},"__N_SSP":true},"page":"/article/[identity]/[[...version]]","query":{"redirect":"/article/rs-9138351","identity":"rs-9138351","version":["v1"]},"buildId":"XKTyCvWXoU3ODBz1xrDgd","isFallback":false,"isExperimentalCompile":false,"dynamicIds":[84888],"gssp":true,"scriptLoader":[]}