Robust Security Framework for IoT-Enabled Smart Cities: Leveraging Ensemble Machine Learning Techniques in Fog Computing Environments

Robust Security Framework for IoT-Enabled Smart Cities: Leveraging Ensemble Machine Learning Techniques in Fog Computing Environments | 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 Short Report Robust Security Framework for IoT-Enabled Smart Cities: Leveraging Ensemble Machine Learning Techniques in Fog Computing Environments Radhika Kumari, Dr. Kiranbir Kaur This is a preprint; it has not been peer reviewed by a journal. https://doi.org/ 10.21203/rs.3.rs-5197026/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 In IoT domains, particularly those reliant on fog computing, possessing enhanced threat detection abilities is crucial. The decentralization and large number of devices, common in smart city environments, make these situations more challenging. Basic security controls are usually inadequate in a complicated and dynamic setting, which calls for innovative approaches to thwarting such intimidation. The gravity of these issues caused the authors to devise a hybrid approach incorporating Gradient Boosting Machines (GBM), Random Forest (RF), and AdaBoost algorithms. The hybrid algorithm combines the advantages of different approaches and minimizes the disadvantages of the individual approaches. The purpose of this research is to conduct an analysis of smart city security literature and assess whether ensemble models are more effective than individual models in the single model approach. The study used two datasets: the University of New South Wales-Network Based 15 (UNSW-NB15) and the Canadian Institute of Cybersecurity Intrusion Detection Systems 2017 (CICIDS2017). The performance metrics of the ensemble model were not only better than that of any single model but also achieved a respectable figure of 95.60% and even 96.67% accuracy on the UNSW-NB15 dataset and CICIDS – 2017, respectively. Key performance metrics showed significant improvements, including precision of 98.78% on UNSW-NB15 and 99.87% on CICIDS2017, recall rates of 99.13% and 99.85%, and F1-scores of 97.32% and 99.64%. These results validate the efficiency of ensemble techniques in safeguarding IoT-based smart city infrastructures, offering enhanced security mechanisms and improved response to evolving cyber threats. Internet of Things Smart Cities fog computing Kernel Principal Component Analysis Gradient Boosting Machine AdaBoost 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-5197026","acceptedTermsAndConditions":true,"allowDirectSubmit":true,"archivedVersions":[],"articleType":"Short Report","associatedPublications":[],"authors":[{"id":367710827,"identity":"610660e6-53dd-4dff-b521-73bf5f496d8b","order_by":0,"name":"Radhika Kumari","email":"data:image/png;base64,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","orcid":"","institution":"Guru Nanak Dev University","correspondingAuthor":true,"prefix":"","firstName":"Radhika","middleName":"","lastName":"Kumari","suffix":""},{"id":367710828,"identity":"b1b19ff7-a3b5-4203-950f-3bd01c5ea67d","order_by":1,"name":"Dr. Kiranbir Kaur","email":"","orcid":"","institution":"Guru Nanak Dev University","correspondingAuthor":false,"prefix":"Dr.","firstName":"Kiranbir","middleName":"","lastName":"Kaur","suffix":""}],"badges":[],"createdAt":"2024-10-03 08:53:12","currentVersionCode":1,"declarations":"","doi":"10.21203/rs.3.rs-5197026/v1","doiUrl":"https://doi.org/10.21203/rs.3.rs-5197026/v1","draftVersion":[],"editorialEvents":[],"editorialNote":"","failedWorkflow":false,"files":[{"id":77420472,"identity":"34a631b2-e065-4cf0-9d88-9bb3355e35c8","added_by":"auto","created_at":"2025-02-28 12:08:47","extension":"pdf","order_by":1,"title":"","display":"","copyAsset":false,"role":"manuscript-pdf","size":579798,"visible":true,"origin":"","legend":"","description":"","filename":"SmartCityPaper.pdf","url":"https://assets-eu.researchsquare.com/files/rs-5197026/v1_covered_ba5610e7-17b2-4595-b9ff-55ab2740b100.pdf"}],"financialInterests":"No competing interests reported.","formattedTitle":"Robust Security Framework for IoT-Enabled Smart Cities: Leveraging Ensemble Machine Learning Techniques in Fog Computing Environments","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":"Internet of Things, Smart Cities, fog computing, Kernel Principal Component Analysis, Gradient Boosting Machine, AdaBoost","lastPublishedDoi":"10.21203/rs.3.rs-5197026/v1","lastPublishedDoiUrl":"https://doi.org/10.21203/rs.3.rs-5197026/v1","license":{"name":"CC BY 4.0","url":"https://creativecommons.org/licenses/by/4.0/"},"manuscriptAbstract":"\u003cp\u003eIn IoT domains, particularly those reliant on fog computing, possessing enhanced threat detection abilities is crucial. The decentralization and large number of devices, common in smart city environments, make these situations more challenging. Basic security controls are usually inadequate in a complicated and dynamic setting, which calls for innovative approaches to thwarting such intimidation. The gravity of these issues caused the authors to devise a hybrid approach incorporating Gradient Boosting Machines (GBM), Random Forest (RF), and AdaBoost algorithms. The hybrid algorithm combines the advantages of different approaches and minimizes the disadvantages of the individual approaches. The purpose of this research is to conduct an analysis of smart city security literature and assess whether ensemble models are more effective than individual models in the single model approach. The study used two datasets: the University of New South Wales-Network Based 15 (UNSW-NB15) and the Canadian Institute of Cybersecurity Intrusion Detection Systems 2017 (CICIDS2017). The performance metrics of the ensemble model were not only better than that of any single model but also achieved a respectable figure of 95.60% and even 96.67% accuracy on the UNSW-NB15 dataset and CICIDS \u0026ndash; 2017, respectively. Key performance metrics showed significant improvements, including precision of 98.78% on UNSW-NB15 and 99.87% on CICIDS2017, recall rates of 99.13% and 99.85%, and F1-scores of 97.32% and 99.64%. These results validate the efficiency of ensemble techniques in safeguarding IoT-based smart city infrastructures, offering enhanced security mechanisms and improved response to evolving cyber threats.\u003c/p\u003e","manuscriptTitle":"Robust Security Framework for IoT-Enabled Smart Cities: Leveraging Ensemble Machine Learning Techniques in Fog Computing Environments","msid":"","msnumber":"","nonDraftVersions":[{"code":1,"date":"2024-10-21 08:41:02","doi":"10.21203/rs.3.rs-5197026/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":"1c1445ed-06a7-4c10-a5ad-3d56468621ad","owner":[],"postedDate":"October 21st, 2024","published":true,"recentEditorialEvents":[],"rejectedJournal":[],"revision":"","amendment":"","status":"posted","subjectAreas":[],"tags":[],"updatedAt":"2025-02-28T12:08:32+00:00","versionOfRecord":[],"versionCreatedAt":"2024-10-21 08:41:02","video":"","vorDoi":"","vorDoiUrl":"","workflowStages":[]},"version":"v1","identity":"rs-5197026","journalConfig":"researchsquare"},"__N_SSP":true},"page":"/article/[identity]/[[...version]]","query":{"redirect":"/article/rs-5197026","identity":"rs-5197026","version":["v1"]},"buildId":"8U1c8b4HqxoKbykW_rLl7","isFallback":false,"isExperimentalCompile":false,"dynamicIds":[84888],"gssp":true,"scriptLoader":[]}