Complexity-Aware Deep Learning Framework for Intrusion Detection in Resource-Constrained Networks

Complexity-Aware Deep Learning Framework for Intrusion Detection in Resource-Constrained Networks | 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 Complexity-Aware Deep Learning Framework for Intrusion Detection in Resource-Constrained Networks Matthew Iwada Ekum, Idris Abiodun Aremu, Chongsheng Zhang, Pearse Oludare Adegbayi, and 1 more This is a preprint; it has not been peer reviewed by a journal. https://doi.org/ 10.21203/rs.3.rs-7908556/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 Artificial intelligence (AI) has emerged as a powerful tool for securing modern networks against increasinglysophisticated cyberattacks. However, many existing AI-basedintrusion detection systems (IDS) prioritise detection accuracywhile neglecting computational complexity, thereby limiting theirapplicability in resource-constrained environments such as Internet of Things (IoT) devices, edge computing nodes, and embeddedsystems. This paper presents a complexity-aware deep learningframework that explicitly integrates algorithmic complexity considerations into the design, feature selection, and learning stagesof IDS models. Rather than introducing a new deep architecture,the framework achieves a favourable accuracy–efficiency tradeoff by coupling gradient-based dynamic feature pruning witha lightweight neural network, supported by theoretical timeand space complexity analysis. Experiments on two benchmarkdatasets (NSL-KDD and CICIDS2017) demonstrate that theproposed method matches or surpasses the accuracy of stateof-the-art models while significantly reducing FLOPs, parameters, and inference cost. The study bridges the gap betweeninformation security, artificial intelligence, and computationalcomplexity theory, offering a simple, theoretically grounded,and reproducible pathway for deploying secure AI systems inresource-constrained environments. Intrusion Detection Systems (IDS) Deep Learning Artificial Intelligence Computational Complexity Feature Pruning Lightweight Models Edge Computing Internet of Things (IoT) 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-7908556","acceptedTermsAndConditions":true,"allowDirectSubmit":true,"archivedVersions":[],"articleType":"Research Article","associatedPublications":[],"authors":[{"id":532489375,"identity":"c6184531-d5cd-46e7-9864-3b1f82085655","order_by":0,"name":"Matthew Iwada Ekum","email":"data:image/png;base64,iVBORw0KGgoAAAANSUhEUgAAAZAAAAAyAQMAAABI0h/eAAAABlBMVEX///8AAABVwtN+AAAACXBIWXMAAA7EAAAOxAGVKw4bAAAA/ElEQVRIiWNgGAWjYDACHjApIccHEzAAcYnRYswGphOI18KQ2Ea0Fn6eM6YbGHMs0tvYjz+T/PnDRt6cgfngbR6GO3YNOLRI9vaY3WDcJpHbxpNjJs2TkGa4s4Et2ZqH4VkyLi0G53mgWhhy2KQZEg4nGBzgAeplOJyMy2H2UC3pbPzPn0n+SPgP1ML/Da8WA16IwxLYJBLMJHgSDoBsYQNpscOlReLMsbIbidskDNsk3hhb86QlG244zGZsOcfgcAIuLfw9ydtufNxWJ8/Pn/7w5g8bO3mD480Pb7ypOGyPSwsYoBrIDHYwQ2IDXj3YAH5bRsEoGAWjYCQBAH2VTgbHNqyQAAAAAElFTkSuQmCC","orcid":"","institution":"Lagos State University of Science and Technology","correspondingAuthor":true,"prefix":"","firstName":"Matthew","middleName":"Iwada","lastName":"Ekum","suffix":""},{"id":532489376,"identity":"6f6fcc91-1c4e-491b-b0bb-84bac3f6dddf","order_by":1,"name":"Idris Abiodun Aremu","email":"","orcid":"","institution":"Lagos State University of Science and Technology","correspondingAuthor":false,"prefix":"","firstName":"Idris","middleName":"Abiodun","lastName":"Aremu","suffix":""},{"id":532489377,"identity":"c53ca08e-daee-4c87-9297-afc7785202a4","order_by":2,"name":"Chongsheng Zhang","email":"","orcid":"","institution":"Henan University","correspondingAuthor":false,"prefix":"","firstName":"Chongsheng","middleName":"","lastName":"Zhang","suffix":""},{"id":532489378,"identity":"620f8348-909f-4e59-9b37-b99d22d1b504","order_by":3,"name":"Pearse Oludare Adegbayi","email":"","orcid":"","institution":"Lagos State University of Science and Technology","correspondingAuthor":false,"prefix":"","firstName":"Pearse","middleName":"Oludare","lastName":"Adegbayi","suffix":""},{"id":532489379,"identity":"e519e757-ac2e-46e5-aedd-1e5f35f177f6","order_by":4,"name":"Albert Ibikunle Idowu","email":"","orcid":"","institution":"Lagos State University of Science and Technology","correspondingAuthor":false,"prefix":"","firstName":"Albert","middleName":"Ibikunle","lastName":"Idowu","suffix":""}],"badges":[],"createdAt":"2025-10-20 20:08:15","currentVersionCode":1,"declarations":"","doi":"10.21203/rs.3.rs-7908556/v1","doiUrl":"https://doi.org/10.21203/rs.3.rs-7908556/v1","draftVersion":[],"editorialEvents":[],"editorialNote":"","failedWorkflow":false,"files":[{"id":94058212,"identity":"6538eada-32d5-4ee4-a68e-5a926f03604b","added_by":"auto","created_at":"2025-10-22 05:31:24","extension":"pdf","order_by":0,"title":"","display":"","copyAsset":false,"role":"acdc-reference","size":984971,"visible":true,"origin":"","legend":"","description":"","filename":"EkumPaper.pdf","url":"https://assets-eu.researchsquare.com/files/rs-7908556/v1/b98086bb428a10c6ab0597fe.pdf"},{"id":94058211,"identity":"6ca9abbd-01cd-4814-8cff-f91e907577b4","added_by":"auto","created_at":"2025-10-22 05:31:24","extension":"json","order_by":1,"title":"","display":"","copyAsset":false,"role":"acdc-reference","size":6817,"visible":true,"origin":"","legend":"","description":"","filename":"c8e834eeca14459a83264c308adbc0d5.json","url":"https://assets-eu.researchsquare.com/files/rs-7908556/v1/869408303f689071b9626a50.json"},{"id":96920071,"identity":"09401c01-6b48-409a-b493-7fd39d87ee37","added_by":"auto","created_at":"2025-11-27 14:14:45","extension":"pdf","order_by":1,"title":"","display":"","copyAsset":false,"role":"manuscript-pdf","size":902767,"visible":true,"origin":"","legend":"","description":"","filename":"EkumPaper.pdf","url":"https://assets-eu.researchsquare.com/files/rs-7908556/v1_covered_f140662a-2622-4cb8-9d81-eb2687caa9ef.pdf"}],"financialInterests":"No competing interests reported.","formattedTitle":"Complexity-Aware Deep Learning Framework for Intrusion Detection in Resource-Constrained Networks","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":"Intrusion Detection Systems (IDS), Deep Learning, Artificial Intelligence, Computational Complexity, Feature Pruning, Lightweight Models, Edge Computing, Internet of Things (IoT)","lastPublishedDoi":"10.21203/rs.3.rs-7908556/v1","lastPublishedDoiUrl":"https://doi.org/10.21203/rs.3.rs-7908556/v1","license":{"name":"CC BY 4.0","url":"https://creativecommons.org/licenses/by/4.0/"},"manuscriptAbstract":"Artificial intelligence (AI) has emerged as a powerful tool for securing modern networks against increasinglysophisticated cyberattacks. However, many existing AI-basedintrusion detection systems (IDS) prioritise detection accuracywhile neglecting computational complexity, thereby limiting theirapplicability in resource-constrained environments such as Internet of Things (IoT) devices, edge computing nodes, and embeddedsystems. This paper presents a complexity-aware deep learningframework that explicitly integrates algorithmic complexity considerations into the design, feature selection, and learning stagesof IDS models. Rather than introducing a new deep architecture,the framework achieves a favourable accuracy–efficiency tradeoff by coupling gradient-based dynamic feature pruning witha lightweight neural network, supported by theoretical timeand space complexity analysis. Experiments on two benchmarkdatasets (NSL-KDD and CICIDS2017) demonstrate that theproposed method matches or surpasses the accuracy of stateof-the-art models while significantly reducing FLOPs, parameters, and inference cost. The study bridges the gap betweeninformation security, artificial intelligence, and computationalcomplexity theory, offering a simple, theoretically grounded,and reproducible pathway for deploying secure AI systems inresource-constrained environments.","manuscriptTitle":"Complexity-Aware Deep Learning Framework for Intrusion Detection in Resource-Constrained Networks","msid":"","msnumber":"","nonDraftVersions":[{"code":1,"date":"2025-10-22 05:31:20","doi":"10.21203/rs.3.rs-7908556/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":"4cd07015-532c-45c2-929e-c2d6fe117c8c","owner":[],"postedDate":"October 22nd, 2025","published":true,"recentEditorialEvents":[],"rejectedJournal":[],"revision":"","amendment":"","status":"posted","subjectAreas":[],"tags":[],"updatedAt":"2025-11-27T06:38:49+00:00","versionOfRecord":[],"versionCreatedAt":"2025-10-22 05:31:20","video":"","vorDoi":"","vorDoiUrl":"","workflowStages":[]},"version":"v1","identity":"rs-7908556","journalConfig":"researchsquare"},"__N_SSP":true},"page":"/article/[identity]/[[...version]]","query":{"redirect":"/article/rs-7908556","identity":"rs-7908556","version":["v1"]},"buildId":"8U1c8b4HqxoKbykW_rLl7","isFallback":false,"isExperimentalCompile":false,"dynamicIds":[84888],"gssp":true,"scriptLoader":[]}