Enhancing Real-Time Intrusion Detection with Variational Autoencoders-Based Dimensionality Reduction and Attention-Driven MLP Classification

Enhancing Real-Time Intrusion Detection with Variational Autoencoders-Based Dimensionality Reduction and Attention-Driven MLP Classification | 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 Enhancing Real-Time Intrusion Detection with Variational Autoencoders-Based Dimensionality Reduction and Attention-Driven MLP Classification Anto Jenisha Immastephy, K PUNITHA This is a preprint; it has not been peer reviewed by a journal. https://doi.org/ 10.21203/rs.3.rs-5713859/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 Real-time intrusion detection is crucial for safeguarding modern networks against evolving cyber threats. Traditional detection systems often face challenges such as high dimensionality, leading to increased computational complexity and reduced detection accuracy. In this paper, we propose an enhanced real-time intrusion detection framework that integrates Variational Autoencoders (VAEs) for dimensionality reduction and an Attention Network in conjunction with a Multi-Layer Perceptron (MLP) for robust classification. The VAE-based dimensionality reduction technique effectively compresses high-dimensional data while preserving key features essential for accurate threat detection. By employing an Attention Network, the model selectively focuses on the most relevant features, improving the classification of both known and unknown intrusion patterns. The MLP serves as the final classifier, utilizing the reduced and attention-refined feature set to provide fast and accurate intrusion detection. Extensive experiments were conducted on benchmark intrusion detection datasets, demonstrating that our proposed model outperforms traditional methods in terms of detection accuracy, computational efficiency, and real-time performance. The combination of VAE for dimensionality reduction and attention-based feature selection with MLP classification presents a powerful approach for enhancing intrusion detection systems, making them more resilient to sophisticated and zero-day attacks. Intrusion Detection Variational Autoencoders Attention Network Multi-Layer Perceptron Dimensionality Reduction 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-5713859","acceptedTermsAndConditions":true,"allowDirectSubmit":true,"archivedVersions":[],"articleType":"Research Article","associatedPublications":[],"authors":[{"id":394951391,"identity":"45213208-2d56-4117-a2be-81b8f75529c5","order_by":0,"name":"Anto Jenisha Immastephy","email":"","orcid":"","institution":"PSR engineering college","correspondingAuthor":false,"prefix":"","firstName":"Anto","middleName":"Jenisha","lastName":"Immastephy","suffix":""},{"id":394951393,"identity":"62599136-ffd1-418c-943e-6cc29f644cf3","order_by":1,"name":"K PUNITHA","email":"data:image/png;base64,iVBORw0KGgoAAAANSUhEUgAAAZAAAAAyAQMAAABI0h/eAAAABlBMVEX///8AAABVwtN+AAAACXBIWXMAAA7EAAAOxAGVKw4bAAAA+ElEQVRIiWNgGAWjYJCCA3AWY4MNiGw8gEspNi1pYJKgFgRgbDiMZggWYHD87MEDP/7ck5Nvb3724eeO83Zr2w8Dbamxicap5UxewsHetmJjgzPHjGf2nrmdvO1MIlDLsbTcBhxaJBtyDA4zNiQkbpBIMGZmbLudbHYAqAXoQtxa+t8YHGb4k1A/f/7zz0At55LNzj/Er4VfAmgLA1tCAsMNHpAtB+zMbhCwhV/ijQHQLwmGG87kFDP2tiUnmN0A2pKAxy9s/DnGH378SZCXbz++meFnm5292fn0hw8+1Njg1IIBEsEqE4hVDgL2pCgeBaNgFIyCkQEAZNxnABkGjpIAAAAASUVORK5CYII=","orcid":"","institution":"PSR engineering college","correspondingAuthor":true,"prefix":"","firstName":"K","middleName":"","lastName":"PUNITHA","suffix":""}],"badges":[],"createdAt":"2024-12-26 05:53:20","currentVersionCode":1,"declarations":"","doi":"10.21203/rs.3.rs-5713859/v1","doiUrl":"https://doi.org/10.21203/rs.3.rs-5713859/v1","draftVersion":[],"editorialEvents":[],"editorialNote":"","failedWorkflow":false,"files":[{"id":72719374,"identity":"5e974e19-c120-4a48-8b2e-5a837ad05836","added_by":"auto","created_at":"2024-12-31 19:31:24","extension":"pdf","order_by":1,"title":"","display":"","copyAsset":false,"role":"manuscript-pdf","size":604325,"visible":true,"origin":"","legend":"","description":"","filename":"Article.pdf","url":"https://assets-eu.researchsquare.com/files/rs-5713859/v1_covered_22929a84-10ed-49c1-b5ba-9467091d503b.pdf"}],"financialInterests":"No competing interests reported.","formattedTitle":"Enhancing Real-Time Intrusion Detection with Variational Autoencoders-Based Dimensionality Reduction and Attention-Driven MLP Classification","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":"Intrusion Detection, Variational Autoencoders, Attention Network, Multi-Layer Perceptron, Dimensionality Reduction","lastPublishedDoi":"10.21203/rs.3.rs-5713859/v1","lastPublishedDoiUrl":"https://doi.org/10.21203/rs.3.rs-5713859/v1","license":{"name":"CC BY 4.0","url":"https://creativecommons.org/licenses/by/4.0/"},"manuscriptAbstract":"\u003cp\u003eReal-time intrusion detection is crucial for safeguarding modern networks against evolving cyber threats. Traditional detection systems often face challenges such as high dimensionality, leading to increased computational complexity and reduced detection accuracy. In this paper, we propose an enhanced real-time intrusion detection framework that integrates Variational Autoencoders (VAEs) for dimensionality reduction and an Attention Network in conjunction with a Multi-Layer Perceptron (MLP) for robust classification. The VAE-based dimensionality reduction technique effectively compresses high-dimensional data while preserving key features essential for accurate threat detection. By employing an Attention Network, the model selectively focuses on the most relevant features, improving the classification of both known and unknown intrusion patterns. The MLP serves as the final classifier, utilizing the reduced and attention-refined feature set to provide fast and accurate intrusion detection. Extensive experiments were conducted on benchmark intrusion detection datasets, demonstrating that our proposed model outperforms traditional methods in terms of detection accuracy, computational efficiency, and real-time performance. The combination of VAE for dimensionality reduction and attention-based feature selection with MLP classification presents a powerful approach for enhancing intrusion detection systems, making them more resilient to sophisticated and zero-day attacks.\u003c/p\u003e","manuscriptTitle":"Enhancing Real-Time Intrusion Detection with Variational Autoencoders-Based Dimensionality Reduction and Attention-Driven MLP Classification","msid":"","msnumber":"","nonDraftVersions":[{"code":1,"date":"2024-12-30 03:25:02","doi":"10.21203/rs.3.rs-5713859/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":"ebd28c52-fd0c-435a-ad4f-b2c02ab4d034","owner":[],"postedDate":"December 30th, 2024","published":true,"recentEditorialEvents":[],"rejectedJournal":[],"revision":"","amendment":"","status":"posted","subjectAreas":[],"tags":[],"updatedAt":"2024-12-31T19:23:16+00:00","versionOfRecord":[],"versionCreatedAt":"2024-12-30 03:25:02","video":"","vorDoi":"","vorDoiUrl":"","workflowStages":[]},"version":"v1","identity":"rs-5713859","journalConfig":"researchsquare"},"__N_SSP":true},"page":"/article/[identity]/[[...version]]","query":{"redirect":"/article/rs-5713859","identity":"rs-5713859","version":["v1"]},"buildId":"qtupq5eGEP_6zYnWcrvyt","isFallback":false,"isExperimentalCompile":false,"dynamicIds":[84888],"gssp":true,"scriptLoader":[]}