PALSYN: A Method for Synthetic Multi-Perspective Event Log Generation with Differential Private Guarantees

PALSYN: A Method for Synthetic Multi-Perspective Event Log Generation with Differential Private Guarantees | 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 PALSYN: A Method for Synthetic Multi-Perspective Event Log Generation with Differential Private Guarantees Martin Kuhn, Joscha Grüger, Ralph Bergmann This is a preprint; it has not been peer reviewed by a journal. https://doi.org/ 10.21203/rs.3.rs-6565248/v2 This work is licensed under a CC BY 4.0 License Status: Published Journal Publication published 19 Dec, 2025 Read the published version in Process Science → Version 2 posted 8 You are reading this latest preprint version Show more versions Abstract The increasing reliance on data-driven technologies such as Artificial Intelligence (AI) and Process Mining has transformed various sectors. Yet, access to real-world data is often restricted by privacy concerns. Synthetic data offers a promising solution by enabling secure data sharing while preserving key characteristics for analysis. This paper introduces the Private Autoregressive Log Synthesizer (PALSYN), a novel approach for generating synthetic event logs with differential privacy guarantees. It employs advanced deep learning techniques to capture the complexity of event data while ensuring privacy. In contrast to existing methods, PALSYN can synthesize private multi-perspective event logs. The evaluation demonstrates the approach's ability to generate synthetic event logs that closely resemble the original data across key metrics. However, the results highlight the inherent privacy-utility tradeoff, with stricter privacy settings introducing noise that strongly impacts utility. By enabling the generation of synthetic event logs with formal privacy guarantees, PALSYN demonstrates significant potential for securely sharing event data in privacy-sensitive domains. Synthetic event logs Process mining Differential privacy Deep learning Generative models Full Text Additional Declarations No competing interests reported. Cite Share Download PDF Status: Published Journal Publication published 19 Dec, 2025 Read the published version in Process Science → Version 2 posted Editorial decision: Revision requested 28 Oct, 2025 Reviews received at journal 28 Oct, 2025 Reviewers agreed at journal 18 Sep, 2025 Reviews received at journal 15 Sep, 2025 Reviewers agreed at journal 10 Sep, 2025 Reviewers invited by journal 26 Aug, 2025 Submission checks completed at journal 21 Aug, 2025 First submitted to journal 21 Aug, 2025 You are reading this latest preprint version Show more versions 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-6565248","acceptedTermsAndConditions":true,"allowDirectSubmit":false,"archivedVersions":[],"articleType":"Research Article","associatedPublications":[],"authors":[{"id":507129880,"identity":"cac3f166-845e-11f0-907b-06cc9d20a69f","order_by":0,"name":"Martin Kuhn","email":"data:image/png;base64,iVBORw0KGgoAAAANSUhEUgAAAZAAAAAyAQMAAABI0h/eAAAABlBMVEX///8AAABVwtN+AAAACXBIWXMAAA7EAAAOxAGVKw4bAAAA2klEQVRIie3Orw+CQBTA8cfYoDxnPTf/BbdjbJfY/FeOsZ3lNoOFSMKk2cAfYjSZ/FFxGrBgIWDTJogb7SAa7pvutvfZewA63b/GASgQMDL0OH6/HRnRj5gURV8CDbFIRaCTTJbHR3bfgkuvq31YcDEGO9gpCTvMnMg/AKO3k7gkXCJgrl7DdsKI/Bg8mkp2HbxCBCKpmpzzliyQ12ReqknabGE1MbE+jEilqEhubPyYuKNUuqOEC7Qw7zpMwPMde846lU5Z8GA6tINMvaaJtE+rz7xOp9Pp1H0AQz1EKWsE5x8AAAAASUVORK5CYII=","orcid":"","institution":"German Research Center for Artificial Intelligence (DFKI)","correspondingAuthor":true,"prefix":"","firstName":"Martin","middleName":"","lastName":"Kuhn","suffix":""},{"id":507129900,"identity":"d4cb7a5f-845e-11f0-907b-06cc9d20a69f","order_by":1,"name":"Joscha Grüger","email":"","orcid":"","institution":"Trier University","correspondingAuthor":false,"prefix":"","firstName":"Joscha","middleName":"","lastName":"Grüger","suffix":""},{"id":507129901,"identity":"e0f62696-845e-11f0-907b-06cc9d20a69f","order_by":2,"name":"Ralph Bergmann","email":"","orcid":"","institution":"Trier University","correspondingAuthor":false,"prefix":"","firstName":"Ralph","middleName":"","lastName":"Bergmann","suffix":""}],"badges":[],"createdAt":"2025-04-30 13:10:30","currentVersionCode":2,"declarations":"","doi":"10.21203/rs.3.rs-6565248/v2","doiUrl":"https://doi.org/10.21203/rs.3.rs-6565248/v2","draftVersion":[],"editorialEvents":[{"content":"https://doi.org/10.1007/s44311-025-00033-5","type":"published","date":"2025-12-20T00:00:00+00:00"}],"editorialNote":"","failedWorkflow":false,"files":[{"id":99550137,"identity":"987f1745-9fd4-43f1-b43a-f1c286f178ed","added_by":"auto","created_at":"2026-01-05 16:57:41","extension":"pdf","order_by":1,"title":"","display":"","copyAsset":false,"role":"manuscript-pdf","size":766291,"visible":true,"origin":"","legend":"","description":"","filename":"2025ProcessScienceJournalREVISIONGeneratingMultiperspectiveSyntheticPrivateEventLogsFINAL.pdf","url":"https://assets-eu.researchsquare.com/files/rs-6565248/v2_covered_7ef55c18-d95c-489e-ad14-a495213eeb13.pdf"}],"financialInterests":"No competing interests reported.","formattedTitle":"PALSYN: A Method for Synthetic Multi-Perspective Event Log Generation with Differential Private Guarantees","fulltext":[],"fulltextSource":"","fullText":"","funders":[],"hasAdminPriorityOnWorkflow":false,"hasManuscriptDocX":false,"hasOptedInToPreprint":true,"hasPassedJournalQc":"","hasAnyPriority":false,"hideJournal":false,"highlight":"","institution":"","isAcceptedByJournal":true,"isAuthorSuppliedPdf":true,"isDeskRejected":"","isHiddenFromSearch":false,"isInQc":false,"isInWorkflow":false,"isPdf":true,"isPdfUpToDate":true,"isWithdrawnOrRetracted":false,"journal":{"display":true,"email":"[email protected]","identity":"process-science","isNatureJournal":false,"hasQc":true,"allowDirectSubmit":false,"externalIdentity":"","sideBox":"Learn more about [Process Science](https://link.springer.com/journal/44311)","snPcode":"44311","submissionUrl":"https://submission.springernature.com/new-submission/44311","title":"Process Science","twitterHandle":"","acdcEnabled":true,"dfaEnabled":true,"editorialSystem":"stoa","reportingPortfolio":"Springer Open","inReviewEnabled":true,"inReviewRevisionsEnabled":true},"keywords":"Synthetic event logs, Process mining, Differential privacy, Deep learning, Generative models","lastPublishedDoi":"10.21203/rs.3.rs-6565248/v2","lastPublishedDoiUrl":"https://doi.org/10.21203/rs.3.rs-6565248/v2","license":{"name":"CC BY 4.0","url":"https://creativecommons.org/licenses/by/4.0/"},"manuscriptAbstract":"The increasing reliance on data-driven technologies such as Artificial Intelligence (AI) and Process Mining has transformed various sectors. Yet, access to real-world data is often restricted by privacy concerns. Synthetic data offers a promising solution by enabling secure data sharing while preserving key characteristics for analysis. This paper introduces the Private Autoregressive Log Synthesizer (PALSYN), a novel approach for generating synthetic event logs with differential privacy guarantees. It employs advanced deep learning techniques to capture the complexity of event data while ensuring privacy. In contrast to existing methods, PALSYN can synthesize private multi-perspective event logs. The evaluation demonstrates the approach's ability to generate synthetic event logs that closely resemble the original data across key metrics. However, the results highlight the inherent privacy-utility tradeoff, with stricter privacy settings introducing noise that strongly impacts utility. By enabling the generation of synthetic event logs with formal privacy guarantees, PALSYN demonstrates significant potential for securely sharing event data in privacy-sensitive domains.","manuscriptTitle":"PALSYN: A Method for Synthetic Multi-Perspective Event Log Generation with Differential Private Guarantees","msid":"","msnumber":"","nonDraftVersions":[{"code":2,"date":"2025-08-28 22:36:01","doi":"10.21203/rs.3.rs-6565248/v2","editorialEvents":[{"type":"communityComments","content":0},{"type":"decision","content":"Revision requested","date":"2025-10-28T21:57:47+00:00","index":"","fulltext":""},{"type":"editorInvitedReview","content":"","date":"2025-10-28T12:59:13+00:00","index":"hide","fulltext":""},{"type":"reviewerAgreed","content":"132469735103951043712998444101408433509","date":"2025-09-18T10:31:23+00:00","index":"hide","fulltext":""},{"type":"editorInvitedReview","content":"","date":"2025-09-15T15:18:09+00:00","index":"hide","fulltext":""},{"type":"reviewerAgreed","content":"268674481536266114014152970749806695748","date":"2025-09-10T07:22:21+00:00","index":"hide","fulltext":""},{"type":"reviewersInvited","content":"","date":"2025-08-27T00:19:06+00:00","index":"","fulltext":""},{"type":"checksComplete","content":"","date":"2025-08-21T21:56:25+00:00","index":"","fulltext":""},{"type":"submitted","content":"Process Science","date":"2025-08-21T09:14:09+00:00","index":"","fulltext":""}],"status":"published","journal":{"display":true,"email":"[email protected]","identity":"process-science","isNatureJournal":false,"hasQc":true,"allowDirectSubmit":false,"externalIdentity":"","sideBox":"Learn more about [Process Science](https://link.springer.com/journal/44311)","snPcode":"44311","submissionUrl":"https://submission.springernature.com/new-submission/44311","title":"Process Science","twitterHandle":"","acdcEnabled":true,"dfaEnabled":true,"editorialSystem":"stoa","reportingPortfolio":"Springer Open","inReviewEnabled":true,"inReviewRevisionsEnabled":true}},{"code":1,"date":"2025-05-07 06:52:40","doi":"10.21203/rs.3.rs-6565248/v1","editorialEvents":[{"type":"communityComments","content":0},{"type":"decision","content":"Revision requested","date":"2025-06-03T01:25:53+00:00","index":"","fulltext":""},{"type":"editorInvitedReview","content":"","date":"2025-06-02T07:41:42+00:00","index":"hide","fulltext":""},{"type":"editorInvitedReview","content":"","date":"2025-05-29T06:31:57+00:00","index":"hide","fulltext":""},{"type":"reviewerAgreed","content":"268674481536266114014152970749806695748","date":"2025-05-13T07:27:11+00:00","index":"hide","fulltext":""},{"type":"reviewerAgreed","content":"45062040747047575669702007112580508886","date":"2025-05-02T07:29:15+00:00","index":"hide","fulltext":""},{"type":"reviewersInvited","content":"","date":"2025-05-02T07:19:00+00:00","index":"","fulltext":""},{"type":"editorAssigned","content":"","date":"2025-05-02T07:10:27+00:00","index":"","fulltext":""},{"type":"checksComplete","content":"","date":"2025-05-02T00:00:01+00:00","index":"","fulltext":""},{"type":"submitted","content":"Process Science","date":"2025-04-30T13:01:58+00:00","index":"","fulltext":""}],"status":"published","journal":{"display":true,"email":"[email protected]","identity":"process-science","isNatureJournal":false,"hasQc":true,"allowDirectSubmit":false,"externalIdentity":"","sideBox":"Learn more about [Process Science](https://link.springer.com/journal/44311)","snPcode":"44311","submissionUrl":"https://submission.springernature.com/new-submission/44311","title":"Process Science","twitterHandle":"","acdcEnabled":true,"dfaEnabled":true,"editorialSystem":"stoa","reportingPortfolio":"Springer Open","inReviewEnabled":true,"inReviewRevisionsEnabled":true}}],"origin":"","ownerIdentity":"27af44a3-44ea-4434-b73c-caf27a08e7f1","owner":[],"postedDate":"August 28th, 2025","published":true,"recentEditorialEvents":[],"rejectedJournal":[],"revision":"","amendment":"","status":"published-in-journal","subjectAreas":[],"tags":[],"updatedAt":"2026-01-05T16:57:36+00:00","versionOfRecord":{"articleIdentity":"rs-6565248","link":"https://doi.org/10.1007/s44311-025-00033-5","journal":{"identity":"process-science","isVorOnly":false,"title":"Process Science"},"publishedOn":"2025-12-20 00:00:00","publishedOnDateReadable":"December 20th, 2025"},"versionCreatedAt":"2025-08-28 22:36:01","video":"","vorDoi":"10.1007/s44311-025-00033-5","vorDoiUrl":"https://doi.org/10.1007/s44311-025-00033-5","workflowStages":[]},"version":"v2","identity":"rs-6565248","journalConfig":"researchsquare"},"__N_SSP":true},"page":"/article/[identity]/[[...version]]","query":{"redirect":"/article/rs-6565248","identity":"rs-6565248","version":["v2"]},"buildId":"8U1c8b4HqxoKbykW_rLl7","isFallback":false,"isExperimentalCompile":false,"dynamicIds":[84888],"gssp":true,"scriptLoader":[]}