DL-DPGAN: A Correlation-Regularized Differentially Private GAN for Privacy-Utility Balanced Synthetic Data Generation

DL-DPGAN: A Correlation-Regularized Differentially Private GAN for Privacy-Utility Balanced Synthetic Data Generation | 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 DL-DPGAN: A Correlation-Regularized Differentially Private GAN for Privacy-Utility Balanced Synthetic Data Generation Mohammad Emadi, Vahideh Moghtadaiee, Mina Alishahi This is a preprint; it has not been peer reviewed by a journal. https://doi.org/ 10.21203/rs.3.rs-9250688/v1 This work is licensed under a CC BY 4.0 License Status: Under Review Version 1 posted 9 You are reading this latest preprint version Abstract Balancing data utility and privacy in machine learning is crucial, particularly in settings where large volumes of sensitive data are collected and analyzed. Generative Adversarial Networks (GANs) and their privacy-preserving variants, Differentially Private GANs (DPGANs), have been employed to create synthetic data that supports privacy protection. However, prior work has shown that, in practice, synthetic data generated by such models can still exhibit privacy risks, especially when trained on confidential data. In this study, we propose Double Loss DPGAN (DL-DPGAN), an enhanced framework that incorporates a correlation-based privacy loss together with the Wasserstein distance to reduce information leakage and improve training stability. To evaluate the model’s performance , we compare the empirical privacy behavior and the quality of the synthetic data generated by DL-DPGAN with those produced by standard GAN and DPGAN baselines. Experiments on multiple benchmark datasets indicate that DL-DPGAN generates synthetic data with strong resistance to distinguisha-bility while maintaining competitive classifier performance compared to these baselines. Overall, DL-DPGAN offers a reasonable balance between privacy protection and model utility, providing a practical approach for privacy-preserving and accurate machine learning. Data Privacy GAN DPGAN DL-DPGAN Synthetic Data Classifier Full Text Additional Declarations No competing interests reported. Cite Share Download PDF Status: Under Review Version 1 posted Reviews received at journal 11 May, 2026 Reviews received at journal 15 Apr, 2026 Reviewers agreed at journal 09 Apr, 2026 Reviewers agreed at journal 08 Apr, 2026 Reviewers agreed at journal 07 Apr, 2026 Reviewers invited by journal 07 Apr, 2026 Editor assigned by journal 05 Apr, 2026 Submission checks completed at journal 30 Mar, 2026 First submitted to journal 28 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-9250688","acceptedTermsAndConditions":true,"allowDirectSubmit":false,"archivedVersions":[],"articleType":"Research Article","associatedPublications":[],"authors":[{"id":620408281,"identity":"9d721afd-acad-4f7e-9b0a-1e0298991039","order_by":0,"name":"Mohammad Emadi","email":"","orcid":"","institution":"Shahid Beheshti University","correspondingAuthor":false,"prefix":"","firstName":"Mohammad","middleName":"","lastName":"Emadi","suffix":""},{"id":620408282,"identity":"dbe747e0-3f44-46d3-b7c3-2aa447e215ab","order_by":1,"name":"Vahideh Moghtadaiee","email":"data:image/png;base64,iVBORw0KGgoAAAANSUhEUgAAAZAAAAAyAQMAAABI0h/eAAAABlBMVEX///8AAABVwtN+AAAACXBIWXMAAA7EAAAOxAGVKw4bAAAA8UlEQVRIiWNgGAWjYJACZiBmbACRH4CYjZ0oLQkQLYwzQFqYidYCYvDALMUHDK4dPvy68IedbH8788HHNr+2yfMxMzB++JiDR8vttDTrGQnJxjMOsyUb5/bdNmxjZmCWnLkNtxbJ2TlmxjwJzIkNh3nMpHN7bjMCtbAx8xLWUp84/zD/99+WPbftCWrhl84xfsyTcDhxw2EeYFj9uJ1IhJa0NGaetOPGGw+zGUv2NtxObmNmbMbrFzbp5MOfeWyqZeedP/zww48/t23ntzcf/PARjxaQLgk4k7ENTDbgVQ8EzB8Q7D+EFI+CUTAKRsFIBAAc0038ch5PwgAAAABJRU5ErkJggg==","orcid":"","institution":"Shahid Beheshti University","correspondingAuthor":true,"prefix":"","firstName":"Vahideh","middleName":"","lastName":"Moghtadaiee","suffix":""},{"id":620408283,"identity":"4c7bb00c-7f15-4f42-8774-87377c623d57","order_by":2,"name":"Mina Alishahi","email":"","orcid":"","institution":"Open Universiteit","correspondingAuthor":false,"prefix":"","firstName":"Mina","middleName":"","lastName":"Alishahi","suffix":""}],"badges":[],"createdAt":"2026-03-28 07:39:11","currentVersionCode":1,"declarations":"","doi":"10.21203/rs.3.rs-9250688/v1","doiUrl":"https://doi.org/10.21203/rs.3.rs-9250688/v1","draftVersion":[],"editorialEvents":[],"editorialNote":"","failedWorkflow":false,"files":[{"id":106895600,"identity":"66ae4355-116d-4320-9150-ed55d3eb3d07","added_by":"auto","created_at":"2026-04-14 14:13:26","extension":"pdf","order_by":1,"title":"","display":"","copyAsset":false,"role":"manuscript-pdf","size":1142915,"visible":true,"origin":"","legend":"","description":"","filename":"DoubleLossDPGANMLcybernetics.pdf","url":"https://assets-eu.researchsquare.com/files/rs-9250688/v1_covered_c3eb69e6-108b-4612-bda6-eddbf5063459.pdf"}],"financialInterests":"No competing interests reported.","formattedTitle":"DL-DPGAN: A Correlation-Regularized Differentially Private GAN for Privacy-Utility Balanced Synthetic Data Generation","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":"international-journal-of-machine-learning-and-cybernetics","isNatureJournal":false,"hasQc":true,"allowDirectSubmit":false,"externalIdentity":"jmlc","sideBox":"Learn more about [International Journal of Machine Learning and Cybernetics](http://actavetscand.biomedcentral.com/)","snPcode":"13042","submissionUrl":"https://submission.nature.com/new-submission/13042/3","title":"International Journal of Machine Learning and Cybernetics","twitterHandle":"","acdcEnabled":true,"dfaEnabled":true,"editorialSystem":"stoa","reportingPortfolio":"Springer Hybrid","inReviewEnabled":true,"inReviewRevisionsEnabled":false},"keywords":"Data Privacy, GAN, DPGAN, DL-DPGAN, Synthetic Data, Classifier","lastPublishedDoi":"10.21203/rs.3.rs-9250688/v1","lastPublishedDoiUrl":"https://doi.org/10.21203/rs.3.rs-9250688/v1","license":{"name":"CC BY 4.0","url":"https://creativecommons.org/licenses/by/4.0/"},"manuscriptAbstract":"Balancing data utility and privacy in machine learning is crucial, particularly in settings where large volumes of sensitive data are collected and analyzed. Generative Adversarial Networks (GANs) and their privacy-preserving variants, Differentially Private GANs (DPGANs), have been employed to create synthetic data that supports privacy protection. However, prior work has shown that, in practice, synthetic data generated by such models can still exhibit privacy risks, especially when trained on confidential data. In this study, we propose Double Loss DPGAN (DL-DPGAN), an enhanced framework that incorporates a correlation-based privacy loss together with the Wasserstein distance to reduce information leakage and improve training stability. To evaluate the model’s performance , we compare the empirical privacy behavior and the quality of the synthetic data generated by DL-DPGAN with those produced by standard GAN and DPGAN baselines. Experiments on multiple benchmark datasets indicate that DL-DPGAN generates synthetic data with strong resistance to distinguisha-bility while maintaining competitive classifier performance compared to these baselines. Overall, DL-DPGAN offers a reasonable balance between privacy protection and model utility, providing a practical approach for privacy-preserving and accurate machine learning.","manuscriptTitle":"DL-DPGAN: A Correlation-Regularized Differentially Private GAN for Privacy-Utility Balanced Synthetic Data Generation","msid":"","msnumber":"","nonDraftVersions":[{"code":1,"date":"2026-04-14 14:12:15","doi":"10.21203/rs.3.rs-9250688/v1","editorialEvents":[{"type":"communityComments","content":0},{"type":"editorInvitedReview","content":"","date":"2026-05-11T07:44:07+00:00","index":"hide","fulltext":""},{"type":"editorInvitedReview","content":"","date":"2026-04-15T08:07:41+00:00","index":"hide","fulltext":""},{"type":"reviewerAgreed","content":"133717644919244251844746883154348123396","date":"2026-04-09T14:28:43+00:00","index":"hide","fulltext":""},{"type":"reviewerAgreed","content":"137353456543779897316094093017761341562","date":"2026-04-08T11:04:10+00:00","index":"hide","fulltext":""},{"type":"reviewerAgreed","content":"182008414351784065472855900775189743513","date":"2026-04-07T14:24:31+00:00","index":"hide","fulltext":""},{"type":"reviewersInvited","content":"","date":"2026-04-07T13:59:10+00:00","index":"","fulltext":""},{"type":"editorAssigned","content":"","date":"2026-04-06T02:34:31+00:00","index":"","fulltext":""},{"type":"checksComplete","content":"","date":"2026-03-30T14:59:16+00:00","index":"","fulltext":""},{"type":"submitted","content":"International Journal of Machine Learning and Cybernetics","date":"2026-03-28T07:29:34+00:00","index":"","fulltext":""}],"status":"published","journal":{"display":true,"email":"[email protected]","identity":"international-journal-of-machine-learning-and-cybernetics","isNatureJournal":false,"hasQc":true,"allowDirectSubmit":false,"externalIdentity":"jmlc","sideBox":"Learn more about [International Journal of Machine Learning and Cybernetics](http://actavetscand.biomedcentral.com/)","snPcode":"13042","submissionUrl":"https://submission.nature.com/new-submission/13042/3","title":"International Journal of Machine Learning and Cybernetics","twitterHandle":"","acdcEnabled":true,"dfaEnabled":true,"editorialSystem":"stoa","reportingPortfolio":"Springer Hybrid","inReviewEnabled":true,"inReviewRevisionsEnabled":false}}],"origin":"","ownerIdentity":"07efea53-9388-40b6-8162-ffc26e042bd4","owner":[],"postedDate":"April 14th, 2026","published":true,"recentEditorialEvents":[{"type":"editorInvitedReview","content":"","date":"2026-05-11T07:44:07+00:00","index":22,"fulltext":""}],"rejectedJournal":[],"revision":"","amendment":"","status":"under-review","subjectAreas":[],"tags":[],"updatedAt":"2026-04-14T14:12:15+00:00","versionOfRecord":[],"versionCreatedAt":"2026-04-14 14:12:15","video":"","vorDoi":"","vorDoiUrl":"","workflowStages":[]},"version":"v1","identity":"rs-9250688","journalConfig":"researchsquare"},"__N_SSP":true},"page":"/article/[identity]/[[...version]]","query":{"redirect":"/article/rs-9250688","identity":"rs-9250688","version":["v1"]},"buildId":"XKTyCvWXoU3ODBz1xrDgd","isFallback":false,"isExperimentalCompile":false,"dynamicIds":[84888],"gssp":true,"scriptLoader":[]}