Adversarially Robust AI for Real-Time Cyber Threat Detection: A Reinforcement Learning Approach

Adversarially Robust AI for Real-Time Cyber Threat Detection: A Reinforcement Learning Approach | 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 Adversarially Robust AI for Real-Time Cyber Threat Detection: A Reinforcement Learning Approach Milad Rahmati This is a preprint; it has not been peer reviewed by a journal. https://doi.org/ 10.21203/rs.3.rs-6198488/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 As cyber threats become increasingly sophisticated, particularly adversarial attacks targeting machine learning models, traditional cybersecurity defenses face significant challenges. Conventional Intrusion Detection Systems (IDS) and anomaly detection methods often struggle against adaptive threats designed to bypass detection mechanisms. This paper introduces a novel reinforcement learning (RL)-based cybersecurity model that enhances adversarial robustness in real-time threat detection. Unlike static machine learning models that remain vulnerable to adversarial manipulations, our approach utilizes adaptive AI agents capable of continuous learning and self-improvement in dynamic cybersecurity environments. The proposed framework integrates deep reinforcement learning (DRL) with adversarial training to strengthen detection mechanisms against evolving cyber threats. By employing policy gradient optimization and reward-based adaptation, the system dynamically adjusts its defense strategies, significantly improving its resilience against adversarial intrusions. Experimental results demonstrate that this approach achieves superior threat detection accuracy, lower false positive rates, and heightened robustness against adversarial attacks compared to traditional machine learning-based security models. This research contributes to the advancement of adversarial machine learning, intelligent cybersecurity automation, and autonomous cyber defense, aligning with the growing need for self-learning security mechanisms in critical infrastructure protection. The proposed RL-based model lays the groundwork for next-generation cybersecurity solutions, enabling AI-driven security frameworks to proactively counter emerging cyber threats in real-time. Artificial Intelligence and Machine Learning Adversarial Machine Learning Reinforcement Learning Cybersecurity Intrusion Detection Deep Learning Threat Detection AI Defense Mechanisms 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-6198488","acceptedTermsAndConditions":true,"allowDirectSubmit":true,"archivedVersions":[],"articleType":"Research Article","associatedPublications":[],"authors":[{"id":426912682,"identity":"23d07069-112b-4b37-86e6-88eb54bfc7cd","order_by":0,"name":"Milad Rahmati","email":"data:image/png;base64,iVBORw0KGgoAAAANSUhEUgAAAZAAAAAyAQMAAABI0h/eAAAABlBMVEX///8AAABVwtN+AAAACXBIWXMAAA7EAAAOxAGVKw4bAAAAq0lEQVRIiWNgGAWjYHACNhBhx0+qFoNkyQZStTBuOECset3Zh589ulHzh9n4Ro7hA4YaO8JazM6lmRvnHDPgM7uRY2zAcCyZCC1nGMykc9gMmM1u5G6TYGxgJkYL+zfpnH8GjJtngLXUE6OFx0w6tw3ofQmwlsNEaSmTzu0zTpY48/6zQcKx40Q5bJt0zjc5O/72tMQHH2qqCWtBBQmkahgFo2AUjIJRgB0AAKQfNFiWSW3FAAAAAElFTkSuQmCC","orcid":"https://orcid.org/0009-0009-8471-0969","institution":"Independent Researcher","correspondingAuthor":true,"prefix":"","firstName":"Milad","middleName":"","lastName":"Rahmati","suffix":""}],"badges":[],"createdAt":"2025-03-10 20:59:11","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-6198488/v1","doiUrl":"https://doi.org/10.21203/rs.3.rs-6198488/v1","draftVersion":[],"editorialEvents":[],"editorialNote":"","failedWorkflow":false,"files":[{"id":78328284,"identity":"d5f1f008-ef30-4ba7-b1be-5a31c0bcff4c","added_by":"auto","created_at":"2025-03-12 06:45:48","extension":"pdf","order_by":1,"title":"","display":"","copyAsset":false,"role":"manuscript-pdf","size":383453,"visible":true,"origin":"","legend":"","description":"","filename":"9AdversariallyRobustAI.pdf","url":"https://assets-eu.researchsquare.com/files/rs-6198488/v1_covered_38837f88-f0b7-4a2c-a45a-5ea410a4b736.pdf"}],"financialInterests":"The authors declare no competing interests.","formattedTitle":"\u003cp\u003e\u003cstrong\u003eAdversarially Robust AI for Real-Time Cyber Threat Detection: A Reinforcement Learning Approach\u003c/strong\u003e\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":"Adversarial Machine Learning, Reinforcement Learning, Cybersecurity, Intrusion Detection, Deep Learning, Threat Detection, AI Defense Mechanisms","lastPublishedDoi":"10.21203/rs.3.rs-6198488/v1","lastPublishedDoiUrl":"https://doi.org/10.21203/rs.3.rs-6198488/v1","license":{"name":"CC BY 4.0","url":"https://creativecommons.org/licenses/by/4.0/"},"manuscriptAbstract":"\u003cp\u003eAs cyber threats become increasingly sophisticated, particularly adversarial attacks targeting machine learning models, traditional cybersecurity defenses face significant challenges. Conventional Intrusion Detection Systems (IDS) and anomaly detection methods often struggle against adaptive threats designed to bypass detection mechanisms. This paper introduces a novel reinforcement learning (RL)-based cybersecurity model that enhances adversarial robustness in real-time threat detection. Unlike static machine learning models that remain vulnerable to adversarial manipulations, our approach utilizes adaptive AI agents capable of continuous learning and self-improvement in dynamic cybersecurity environments.\u003c/p\u003e \u003cp\u003eThe proposed framework integrates deep reinforcement learning (DRL) with adversarial training to strengthen detection mechanisms against evolving cyber threats. By employing policy gradient optimization and reward-based adaptation, the system dynamically adjusts its defense strategies, significantly improving its resilience against adversarial intrusions. Experimental results demonstrate that this approach achieves superior threat detection accuracy, lower false positive rates, and heightened robustness against adversarial attacks compared to traditional machine learning-based security models.\u003c/p\u003e \u003cp\u003eThis research contributes to the advancement of adversarial machine learning, intelligent cybersecurity automation, and autonomous cyber defense, aligning with the growing need for self-learning security mechanisms in critical infrastructure protection. The proposed RL-based model lays the groundwork for next-generation cybersecurity solutions, enabling AI-driven security frameworks to proactively counter emerging cyber threats in real-time.\u003c/p\u003e","manuscriptTitle":"Adversarially Robust AI for Real-Time Cyber Threat Detection: A Reinforcement Learning Approach","msid":"","msnumber":"","nonDraftVersions":[{"code":1,"date":"2025-03-12 06:29:43","doi":"10.21203/rs.3.rs-6198488/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":"05f8bdcd-d589-4d0b-a30e-5439f552fe5b","owner":[],"postedDate":"March 12th, 2025","published":true,"recentEditorialEvents":[],"rejectedJournal":[],"revision":"","amendment":"","status":"posted","subjectAreas":[{"id":45488657,"name":"Artificial Intelligence and Machine Learning"}],"tags":[],"updatedAt":"2025-03-12T06:29:43+00:00","versionOfRecord":[],"versionCreatedAt":"2025-03-12 06:29:43","video":"","vorDoi":"","vorDoiUrl":"","workflowStages":[]},"version":"v1","identity":"rs-6198488","journalConfig":"researchsquare"},"__N_SSP":true},"page":"/article/[identity]/[[...version]]","query":{"redirect":"/article/rs-6198488","identity":"rs-6198488","version":["v1"]},"buildId":"8U1c8b4HqxoKbykW_rLl7","isFallback":false,"isExperimentalCompile":false,"dynamicIds":[84888],"gssp":true,"scriptLoader":[]}