Optimizing K-Means Clustering with Privacy Budget Allocation Based on Variance and Sensitivity

Optimizing K-Means Clustering with Privacy Budget Allocation Based on Variance and Sensitivity | 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 Optimizing K-Means Clustering with Privacy Budget Allocation Based on Variance and Sensitivity Afzal Ali, Sreemoyee Biswas, Nilay Khare, Mansi Gyanchandani This is a preprint; it has not been peer reviewed by a journal. https://doi.org/ 10.21203/rs.3.rs-6086086/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 This paper presents a novel approach for enhancing k-means clustering through a privacy-preserving budget allocation mechanism based on variance and sensitivity analysis. The proposed method aims to balance the trade-off between data utility and privacy preservation by selectively allocating privacy budgets across features, emphasizing features with higher variance and lower sensitivity to maintain clustering accuracy. We employ differential privacy techniques, particularly the Laplace mechanism, to introduce controlled noise, protecting user data while minimizing information loss. Comparative analysis with traditional uniform privacy allocation reveals that our approach better preserves cluster cohesion and separation, resulting in superior performance in clustering tasks. Experiments conducted on healthcare datasets demonstrate the efficacy of the proposed strategy in achieving robust privacy guarantees with minimal impact on clustering utility, making it suitable for sensitive data analysis scenarios. Data privacy Differential privacy K-anonymity K-means clustering Laplace Mechanism. 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-6086086","acceptedTermsAndConditions":true,"allowDirectSubmit":true,"archivedVersions":[],"articleType":"Research Article","associatedPublications":[],"authors":[{"id":455319949,"identity":"256a1f8f-10d6-4586-a2f3-57cbd07dfb16","order_by":0,"name":"Afzal Ali","email":"data:image/png;base64,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","orcid":"","institution":"MANIT Bhopal","correspondingAuthor":true,"prefix":"","firstName":"Afzal","middleName":"","lastName":"Ali","suffix":""},{"id":455319950,"identity":"bc458bc2-73d1-4102-9120-66bd539a7d80","order_by":1,"name":"Sreemoyee Biswas","email":"","orcid":"","institution":"MANIT Bhopal","correspondingAuthor":false,"prefix":"","firstName":"Sreemoyee","middleName":"","lastName":"Biswas","suffix":""},{"id":455319951,"identity":"a64d37bc-c977-4bd8-84b4-b26bda1d89d9","order_by":2,"name":"Nilay Khare","email":"","orcid":"","institution":"MANIT Bhopal","correspondingAuthor":false,"prefix":"","firstName":"Nilay","middleName":"","lastName":"Khare","suffix":""},{"id":455319952,"identity":"610539ed-2db0-406c-911d-d603bd833f0c","order_by":3,"name":"Mansi Gyanchandani","email":"","orcid":"","institution":"MANIT Bhopal","correspondingAuthor":false,"prefix":"","firstName":"Mansi","middleName":"","lastName":"Gyanchandani","suffix":""}],"badges":[],"createdAt":"2025-02-22 14:23:21","currentVersionCode":1,"declarations":"","doi":"10.21203/rs.3.rs-6086086/v1","doiUrl":"https://doi.org/10.21203/rs.3.rs-6086086/v1","draftVersion":[],"editorialEvents":[],"editorialNote":"","failedWorkflow":false,"files":[{"id":83795755,"identity":"69f3f1b5-a092-4a76-baba-c57f3900b56b","added_by":"auto","created_at":"2025-06-03 00:01:26","extension":"pdf","order_by":1,"title":"","display":"","copyAsset":false,"role":"manuscript-pdf","size":521544,"visible":true,"origin":"","legend":"","description":"","filename":"ClusterComputingJournal6.pdf","url":"https://assets-eu.researchsquare.com/files/rs-6086086/v1_covered_37547c59-a672-41df-8049-6a2d2ae71172.pdf"}],"financialInterests":"No competing interests reported.","formattedTitle":"Optimizing K-Means Clustering with Privacy Budget Allocation Based on Variance and Sensitivity","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":"Data privacy, Differential privacy, K-anonymity, K-means clustering, Laplace Mechanism.","lastPublishedDoi":"10.21203/rs.3.rs-6086086/v1","lastPublishedDoiUrl":"https://doi.org/10.21203/rs.3.rs-6086086/v1","license":{"name":"CC BY 4.0","url":"https://creativecommons.org/licenses/by/4.0/"},"manuscriptAbstract":"\u003cp\u003eThis paper presents a novel approach for enhancing k-means clustering through a privacy-preserving budget allocation mechanism based on variance and sensitivity analysis. The proposed method aims to balance the trade-off between data utility and privacy preservation by selectively allocating privacy budgets across features, emphasizing features with higher variance and lower sensitivity to maintain clustering accuracy. We employ differential privacy techniques, particularly the Laplace mechanism, to introduce controlled noise, protecting user data while minimizing information loss. Comparative analysis with traditional uniform privacy allocation reveals that our approach better preserves cluster cohesion and separation, resulting in superior performance in clustering tasks. Experiments conducted on healthcare datasets demonstrate the efficacy of the proposed strategy in achieving robust privacy guarantees with minimal impact on clustering utility, making it suitable for sensitive data analysis scenarios.\u003c/p\u003e","manuscriptTitle":"Optimizing K-Means Clustering with Privacy Budget Allocation Based on Variance and Sensitivity","msid":"","msnumber":"","nonDraftVersions":[{"code":1,"date":"2025-05-14 11:32:39","doi":"10.21203/rs.3.rs-6086086/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":"d3489ad6-6042-4d36-84ec-16edd945e18b","owner":[],"postedDate":"May 14th, 2025","published":true,"recentEditorialEvents":[],"rejectedJournal":[],"revision":"","amendment":"","status":"posted","subjectAreas":[],"tags":[],"updatedAt":"2025-06-02T23:53:18+00:00","versionOfRecord":[],"versionCreatedAt":"2025-05-14 11:32:39","video":"","vorDoi":"","vorDoiUrl":"","workflowStages":[]},"version":"v1","identity":"rs-6086086","journalConfig":"researchsquare"},"__N_SSP":true},"page":"/article/[identity]/[[...version]]","query":{"redirect":"/article/rs-6086086","identity":"rs-6086086","version":["v1"]},"buildId":"8U1c8b4HqxoKbykW_rLl7","isFallback":false,"isExperimentalCompile":false,"dynamicIds":[84888],"gssp":true,"scriptLoader":[]}