An AI-Enabled Zero‑Trust Framework for Security Validation Platforms

An AI-Enabled Zero‑Trust Framework for Security Validation Platforms | 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 An AI-Enabled Zero‑Trust Framework for Security Validation Platforms Prashant Vajpayee, Binod Tandan, Gahangir Hossain This is a preprint; it has not been peer reviewed by a journal. https://doi.org/ 10.21203/rs.3.rs-9397236/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 rapid adoption of autonomous and agentic Artificial Intelligence (AI) systems has intensified the need for rigorous, transparent, and continuously verifiable security controls. This paper presents a unified framework for a Zero‑Trust AI Security Validation Platform that integrates pillar‑wise machine‑learning models, risk‑aware trust scoring, strict policy enforcement, and a tamper‑evident hash‑chain ledger. The framework models AI behavior across five core Zero‑Trust pillars—Identity, Device, Network, Application, and Data—using a hybrid approach that combines supervised Random Forest classifiers with an unsupervised Isolation Forest for anomaly detection. These pillar‑specific risks are fused into a dynamic trust score, which is evaluated against sensitivity‑aware thresholds and non‑negotiable Zero‑Trust policy gates to produce transparent allow/deny decisions. Each decision, along with its full contextual reasoning, is immutably recorded in a blockchain‑like ledger, enabling traceability, auditability, and detection of model‑drift. Although demonstrated using synthetic telemetry, the architecture is directly applicable to enterprise AI environments and critical infrastructure systems, where auditability, continuous validation, and tamper‑evident logging are essential. The results show that the framework achieves high detection accuracy, perfect recall for attack scenarios, and strong alignment with emerging AI governance and Zero‑Trust security standards. This work provides a practical, extensible foundation for validating the safety, integrity, and trustworthiness of AI systems operating in high‑risk environments. Artificial Intelligence and Machine Learning Zero Trust Secure AI Block Chain Cyber Risk Cybersecurity Machine Learning 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-9397236","acceptedTermsAndConditions":true,"allowDirectSubmit":true,"archivedVersions":[],"articleType":"Research Article","associatedPublications":[],"authors":[{"id":621845267,"identity":"dd8ae409-bf17-41b4-9bd5-70122cec5b5a","order_by":0,"name":"Prashant Vajpayee","email":"data:image/png;base64,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","orcid":"","institution":"University of North Texas","correspondingAuthor":true,"prefix":"","firstName":"Prashant","middleName":"","lastName":"Vajpayee","suffix":""},{"id":621845269,"identity":"32cc0ad5-249f-449f-91f5-d7ff54caebf7","order_by":1,"name":"Binod Tandan","email":"","orcid":"","institution":"University of North Texas","correspondingAuthor":false,"prefix":"","firstName":"Binod","middleName":"","lastName":"Tandan","suffix":""},{"id":621845416,"identity":"f36d741b-be3d-4d30-8153-258d3985ae87","order_by":2,"name":"Gahangir Hossain","email":"data:image/png;base64,iVBORw0KGgoAAAANSUhEUgAAAZAAAAAyAQMAAABI0h/eAAAABlBMVEX///8AAABVwtN+AAAACXBIWXMAAA7EAAAOxAGVKw4bAAABCUlEQVRIiWNgGAWjYBAC/gYeECUBRAkQBj9EghmnFokD6FokGxgYG/BpMWDggWlOgIocIKSF/ezBzwW/LPIZJJIPf/xRY5FnfCP3+AOGCuvEBlxaePKSpWf2SVg2yD9Lk+Y5JlFsdiMPqPpMOk4thgdyDKR5eyQMGCRyzJgZ2CQSt93IMWxgbDuM25bzb4x/Q7UYf/zxTyJx8wyQln94tNzIMZPm+QHWYiDB2yaRuEECpKUBtxaJG2/MrHkbJAzYJNLSpHn7JBJnnHljOCPhWLoxLi38/TnGt3n+1Bnwg0PsW11if3uOwYcPNdayuLSAAWMbAwMbikgCPuVg8IegilEwCkbBKBjJAADMRFdGBOXFCwAAAABJRU5ErkJggg==","orcid":"","institution":"University of North Texas","correspondingAuthor":true,"prefix":"","firstName":"Gahangir","middleName":"","lastName":"Hossain","suffix":""}],"badges":[],"createdAt":"2026-04-13 00:09:49","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-9397236/v1","doiUrl":"https://doi.org/10.21203/rs.3.rs-9397236/v1","draftVersion":[],"editorialEvents":[],"editorialNote":"","failedWorkflow":false,"files":[{"id":106961380,"identity":"d293d6ae-c55b-4052-ac8c-c0cc8da6c5af","added_by":"auto","created_at":"2026-04-15 09:25:20","extension":"pdf","order_by":1,"title":"","display":"","copyAsset":false,"role":"manuscript-pdf","size":795626,"visible":true,"origin":"","legend":"","description":"","filename":"PrashantVajpayeeZeroTrustAISecurityPlatformJournalPaperApril2026.pdf","url":"https://assets-eu.researchsquare.com/files/rs-9397236/v1_covered_e9d1c1e8-de50-4471-b996-d707a1f50a6f.pdf"}],"financialInterests":"The authors declare no competing interests.","formattedTitle":"\u003cp\u003eAn AI-Enabled Zero‑Trust Framework for Security Validation Platforms\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":"Zero Trust, Secure AI, Block Chain, Cyber Risk, Cybersecurity, Machine Learning","lastPublishedDoi":"10.21203/rs.3.rs-9397236/v1","lastPublishedDoiUrl":"https://doi.org/10.21203/rs.3.rs-9397236/v1","license":{"name":"CC BY 4.0","url":"https://creativecommons.org/licenses/by/4.0/"},"manuscriptAbstract":"\u003cp\u003eThe rapid adoption of autonomous and agentic Artificial Intelligence (AI) systems has intensified the need for rigorous, transparent, and continuously verifiable security controls. This paper presents a unified framework for a Zero‑Trust AI Security Validation Platform that integrates pillar‑wise machine‑learning models, risk‑aware trust scoring, strict policy enforcement, and a tamper‑evident hash‑chain ledger. The framework models AI behavior across five core Zero‑Trust pillars\u0026mdash;Identity, Device, Network, Application, and Data\u0026mdash;using a hybrid approach that combines supervised Random Forest classifiers with an unsupervised Isolation Forest for anomaly detection. These pillar‑specific risks are fused into a dynamic trust score, which is evaluated against sensitivity‑aware thresholds and non‑negotiable Zero‑Trust policy gates to produce transparent allow/deny decisions. Each decision, along with its full contextual reasoning, is immutably recorded in a blockchain‑like ledger, enabling traceability, auditability, and detection of model‑drift. Although demonstrated using synthetic telemetry, the architecture is directly applicable to enterprise AI environments and critical infrastructure systems, where auditability, continuous validation, and tamper‑evident logging are essential. The results show that the framework achieves high detection accuracy, perfect recall for attack scenarios, and strong alignment with emerging AI governance and Zero‑Trust security standards. This work provides a practical, extensible foundation for validating the safety, integrity, and trustworthiness of AI systems operating in high‑risk environments.\u003c/p\u003e","manuscriptTitle":"An AI-Enabled Zero‑Trust Framework for Security Validation Platforms","msid":"","msnumber":"","nonDraftVersions":[{"code":1,"date":"2026-04-14 14:35:50","doi":"10.21203/rs.3.rs-9397236/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":"2987f290-d2c1-4a68-b765-0993e79c7152","owner":[],"postedDate":"April 14th, 2026","published":true,"recentEditorialEvents":[],"rejectedJournal":[],"revision":"","amendment":"","status":"posted","subjectAreas":[{"id":66170087,"name":"Artificial Intelligence and Machine Learning"}],"tags":[],"updatedAt":"2026-04-14T14:35:50+00:00","versionOfRecord":[],"versionCreatedAt":"2026-04-14 14:35:50","video":"","vorDoi":"","vorDoiUrl":"","workflowStages":[]},"version":"v1","identity":"rs-9397236","journalConfig":"researchsquare"},"__N_SSP":true},"page":"/article/[identity]/[[...version]]","query":{"redirect":"/article/rs-9397236","identity":"rs-9397236","version":["v1"]},"buildId":"XKTyCvWXoU3ODBz1xrDgd","isFallback":false,"isExperimentalCompile":false,"dynamicIds":[84888],"gssp":true,"scriptLoader":[]}