A CNN–LSTM Hybrid Model for Reducing False Positives in Anomaly-Based Intrusion Detection Systems

A CNN–LSTM Hybrid Model for Reducing False Positives in Anomaly-Based Intrusion Detection Systems | 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 A CNN–LSTM Hybrid Model for Reducing False Positives in Anomaly-Based Intrusion Detection Systems Sameer Tembhurney, Tripti Arjariya This is a preprint; it has not been peer reviewed by a journal. https://doi.org/ 10.21203/rs.3.rs-9244380/v1 This work is licensed under a CC BY 4.0 License Status: Under Review Version 1 posted 15 You are reading this latest preprint version Abstract The rapid expansion of next-generation networks has heightened the risk of sophis- ticated cyber intrusions, making anomaly-based intrusion detection systems (IDS) a critical component of modern cybersecurity. Traditional IDS techniques, while effec- tive in detecting known attacks, often suffer from high false positive rates and limited adaptability to evolving threats. To address these challenges, this paper proposes a hybrid deep learning framework that integrates Convolutional Neural Networks (CNN) and Long Short-Term Memory (LSTM) models for efficient intrusion detection. CNN layers are employed to extract spatial patterns from traffic features, while LSTM units capture temporal dependencies in sequential data, enabling the system to detect both short-lived and long-range anomalies. To further enhance generalization, regularization strategies and post-processing mechanisms are incorporated for false positive suppres- sion. The proposed model is evaluated on benchmark datasets such as NSL-KDD, CIC- IDS2017, and UNSW-NB15, achieving significant improvements in accuracy, detection rate, and false positive reduction compared to conventional machine learning and deep learning baselines. The results demonstrate that the CNN–LSTM hybrid model pro- vides a scalable and intelligent IDS solution, capable of strengthening network defense mechanisms for next-generation autonomous and heterogeneous environments. Intrusion Detection Anomaly Detection CNN LSTM False Positives Net- work Security Full Text Additional Declarations No competing interests reported. Cite Share Download PDF Status: Under Review Version 1 posted Reviews received at journal 15 May, 2026 Reviews received at journal 09 May, 2026 Reviewers agreed at journal 08 May, 2026 Reviews received at journal 07 May, 2026 Reviews received at journal 07 May, 2026 Reviews received at journal 04 May, 2026 Reviewers agreed at journal 04 May, 2026 Reviewers agreed at journal 03 May, 2026 Reviewers agreed at journal 02 May, 2026 Reviewers agreed at journal 30 Apr, 2026 Reviewers agreed at journal 30 Apr, 2026 Reviewers invited by journal 30 Apr, 2026 Editor assigned by journal 13 Apr, 2026 Submission checks completed at journal 13 Apr, 2026 First submitted to journal 27 Mar, 2026 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-9244380","acceptedTermsAndConditions":true,"allowDirectSubmit":false,"archivedVersions":[],"articleType":"Research Article","associatedPublications":[],"authors":[{"id":636229511,"identity":"5c51a4c1-0e05-43f6-8f71-c19db7473c39","order_by":0,"name":"Sameer Tembhurney","email":"","orcid":"","institution":"Bhabha University","correspondingAuthor":false,"prefix":"","firstName":"Sameer","middleName":"","lastName":"Tembhurney","suffix":""},{"id":636229512,"identity":"dfb01dc4-c459-4632-a09c-442f33930ca8","order_by":1,"name":"Tripti Arjariya","email":"data:image/png;base64,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","orcid":"","institution":"Bhabha University","correspondingAuthor":true,"prefix":"","firstName":"Tripti","middleName":"","lastName":"Arjariya","suffix":""}],"badges":[],"createdAt":"2026-03-27 11:53:10","currentVersionCode":1,"declarations":"","doi":"10.21203/rs.3.rs-9244380/v1","doiUrl":"https://doi.org/10.21203/rs.3.rs-9244380/v1","draftVersion":[],"editorialEvents":[],"editorialNote":"","failedWorkflow":false,"files":[{"id":108762853,"identity":"a13ec114-527e-4645-85ef-9157545969ce","added_by":"auto","created_at":"2026-05-08 07:07:34","extension":"pdf","order_by":1,"title":"","display":"","copyAsset":false,"role":"manuscript-pdf","size":784295,"visible":true,"origin":"","legend":"","description":"","filename":"INTRUSIONDETECTIONPAPERSAMEERTEMBHURNEYSIR131.pdf","url":"https://assets-eu.researchsquare.com/files/rs-9244380/v1_covered_ab0fe44d-8d6f-46a4-8b91-598aae005719.pdf"}],"financialInterests":"No competing interests reported.","formattedTitle":"A CNN–LSTM Hybrid Model for Reducing False Positives in Anomaly-Based Intrusion Detection Systems","fulltext":[],"fulltextSource":"","fullText":"","funders":[],"hasAdminPriorityOnWorkflow":false,"hasManuscriptDocX":false,"hasOptedInToPreprint":true,"hasPassedJournalQc":"","hasAnyPriority":false,"hideJournal":false,"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":"discover-applied-sciences","isNatureJournal":false,"hasQc":true,"allowDirectSubmit":false,"externalIdentity":"","sideBox":"Learn more about [Discover Applied Sciences](https://link.springer.com/journal/42452)","snPcode":"42452","submissionUrl":"https://submission.springernature.com/new-submission/42452/3","title":"Discover Applied Sciences","twitterHandle":"","acdcEnabled":true,"dfaEnabled":true,"editorialSystem":"stoa","reportingPortfolio":"Discover Series","inReviewEnabled":true,"inReviewRevisionsEnabled":true},"keywords":"Intrusion Detection, Anomaly Detection, CNN, LSTM, False Positives, Net- work Security","lastPublishedDoi":"10.21203/rs.3.rs-9244380/v1","lastPublishedDoiUrl":"https://doi.org/10.21203/rs.3.rs-9244380/v1","license":{"name":"CC BY 4.0","url":"https://creativecommons.org/licenses/by/4.0/"},"manuscriptAbstract":"\u003cp\u003eThe rapid expansion of next-generation networks has heightened the risk of sophis- ticated cyber intrusions, making anomaly-based intrusion detection systems (IDS) a critical component of modern cybersecurity. Traditional IDS techniques, while effec- tive in detecting known attacks, often suffer from high false positive rates and limited adaptability to evolving threats. To address these challenges, this paper proposes a hybrid deep learning framework that integrates Convolutional Neural Networks (CNN) and Long Short-Term Memory (LSTM) models for efficient intrusion detection. CNN layers are employed to extract spatial patterns from traffic features, while LSTM units capture temporal dependencies in sequential data, enabling the system to detect both short-lived and long-range anomalies. To further enhance generalization, regularization strategies and post-processing mechanisms are incorporated for false positive suppres- sion. The proposed model is evaluated on benchmark datasets such as NSL-KDD, CIC- IDS2017, and UNSW-NB15, achieving significant improvements in accuracy, detection rate, and false positive reduction compared to conventional machine learning and deep learning baselines. The results demonstrate that the CNN\u0026ndash;LSTM hybrid model pro- vides a scalable and intelligent IDS solution, capable of strengthening network defense mechanisms for next-generation autonomous and heterogeneous environments.\u003c/p\u003e","manuscriptTitle":"A CNN–LSTM Hybrid Model for Reducing False Positives in Anomaly-Based Intrusion Detection Systems","msid":"","msnumber":"","nonDraftVersions":[{"code":1,"date":"2026-05-08 07:07:14","doi":"10.21203/rs.3.rs-9244380/v1","editorialEvents":[{"type":"communityComments","content":0},{"type":"editorInvitedReview","content":"","date":"2026-05-16T01:33:35+00:00","index":"hide","fulltext":""},{"type":"editorInvitedReview","content":"","date":"2026-05-09T08:27:30+00:00","index":"hide","fulltext":""},{"type":"reviewerAgreed","content":"177049772278098788571366224218411649718","date":"2026-05-08T13:29:54+00:00","index":"hide","fulltext":""},{"type":"editorInvitedReview","content":"","date":"2026-05-07T13:15:40+00:00","index":"hide","fulltext":""},{"type":"editorInvitedReview","content":"","date":"2026-05-07T11:11:48+00:00","index":"hide","fulltext":""},{"type":"editorInvitedReview","content":"","date":"2026-05-04T09:41:40+00:00","index":"hide","fulltext":""},{"type":"reviewerAgreed","content":"103229692432031574000645795648526436530","date":"2026-05-04T09:06:30+00:00","index":"hide","fulltext":""},{"type":"reviewerAgreed","content":"297031380061208904743975805248953022659","date":"2026-05-03T11:15:05+00:00","index":"hide","fulltext":""},{"type":"reviewerAgreed","content":"287960912295339697259913672374558662168","date":"2026-05-02T10:25:18+00:00","index":"hide","fulltext":""},{"type":"reviewerAgreed","content":"119827641910603195908343826815400602044","date":"2026-04-30T14:32:17+00:00","index":"hide","fulltext":""},{"type":"reviewerAgreed","content":"213846804433618427812381750138523457966","date":"2026-04-30T09:50:43+00:00","index":"hide","fulltext":""},{"type":"reviewersInvited","content":"","date":"2026-04-30T09:36:20+00:00","index":"","fulltext":""},{"type":"editorAssigned","content":"","date":"2026-04-13T07:14:41+00:00","index":"","fulltext":""},{"type":"checksComplete","content":"","date":"2026-04-13T07:13:49+00:00","index":"","fulltext":""},{"type":"submitted","content":"Discover Applied Sciences","date":"2026-03-27T11:35:39+00:00","index":"","fulltext":""}],"status":"published","journal":{"display":true,"email":"[email protected]","identity":"discover-applied-sciences","isNatureJournal":false,"hasQc":true,"allowDirectSubmit":false,"externalIdentity":"","sideBox":"Learn more about [Discover Applied Sciences](https://link.springer.com/journal/42452)","snPcode":"42452","submissionUrl":"https://submission.springernature.com/new-submission/42452/3","title":"Discover Applied Sciences","twitterHandle":"","acdcEnabled":true,"dfaEnabled":true,"editorialSystem":"stoa","reportingPortfolio":"Discover Series","inReviewEnabled":true,"inReviewRevisionsEnabled":true}}],"origin":"","ownerIdentity":"60621361-1ae2-4c58-97a1-7ae24694bd10","owner":[],"postedDate":"May 8th, 2026","published":true,"recentEditorialEvents":[{"type":"editorInvitedReview","content":"","date":"2026-05-16T01:33:35+00:00","index":44,"fulltext":""},{"type":"editorInvitedReview","content":"","date":"2026-05-09T08:27:30+00:00","index":43,"fulltext":""},{"type":"reviewerAgreed","content":"177049772278098788571366224218411649718","date":"2026-05-08T13:29:54+00:00","index":42,"fulltext":""},{"type":"editorInvitedReview","content":"","date":"2026-05-07T13:15:40+00:00","index":41,"fulltext":""},{"type":"editorInvitedReview","content":"","date":"2026-05-07T11:11:48+00:00","index":40,"fulltext":""},{"type":"editorInvitedReview","content":"","date":"2026-05-04T09:41:40+00:00","index":39,"fulltext":""},{"type":"reviewerAgreed","content":"103229692432031574000645795648526436530","date":"2026-05-04T09:06:30+00:00","index":38,"fulltext":""},{"type":"reviewerAgreed","content":"297031380061208904743975805248953022659","date":"2026-05-03T11:15:05+00:00","index":37,"fulltext":""},{"type":"reviewerAgreed","content":"287960912295339697259913672374558662168","date":"2026-05-02T10:25:18+00:00","index":35,"fulltext":""},{"type":"reviewerAgreed","content":"119827641910603195908343826815400602044","date":"2026-04-30T14:32:17+00:00","index":34,"fulltext":""},{"type":"reviewerAgreed","content":"213846804433618427812381750138523457966","date":"2026-04-30T09:50:43+00:00","index":33,"fulltext":""},{"type":"reviewersInvited","content":"15","date":"2026-04-30T09:36:20+00:00","index":"","fulltext":""}],"rejectedJournal":[],"revision":"","amendment":"","status":"under-review","subjectAreas":[],"tags":[],"updatedAt":"2026-05-08T07:07:14+00:00","versionOfRecord":[],"versionCreatedAt":"2026-05-08 07:07:14","video":"","vorDoi":"","vorDoiUrl":"","workflowStages":[]},"version":"v1","identity":"rs-9244380","journalConfig":"researchsquare"},"__N_SSP":true},"page":"/article/[identity]/[[...version]]","query":{"redirect":"/article/rs-9244380","identity":"rs-9244380","version":["v1"]},"buildId":"XKTyCvWXoU3ODBz1xrDgd","isFallback":false,"isExperimentalCompile":false,"dynamicIds":[84888],"gssp":true,"scriptLoader":[]}