A Unified Traceability Framework for Diffusion Model Generated Images

A Unified Traceability Framework for Diffusion Model Generated Images | 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 Article A Unified Traceability Framework for Diffusion Model Generated Images Guomin Gu, Jintao Yu, Xiaojuan Wang, Haibing Zheng, Jinyin Chen, and 1 more This is a preprint; it has not been peer reviewed by a journal. https://doi.org/ 10.21203/rs.3.rs-8404442/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 Nowadays, diffusion models have become dominant generative tools capable of producing highly realistic images, while triggering new challenges for image provenance verification. Traditional content-based and metadata-based traceability methods fail to reliably distinguish synthetic from authentic images, while existing learning-based approaches face scalability and robustness limitations. To bridge the gap, we propose a novel unified traceability framework that integrates two complementary strategies: Arcits and Aswomts. Specifically, Arcits targets image-level provenance by exploiting reconstruction residuals as image fingerprints and combining them with lightweight model fingerprints extracted from the U-Net architecture. Aswomts extends to model-level provenance by encoding structural and weight information of diffusion models via graph neural networks and weighted similarity modeling, enabling the quantification of model similarity. Comprehensive experiments on multiple datasets demonstrate that Arcits outperforms baseline methods such as PRNU, KNN, ResNet50, and VGG16 in accuracy and robustness against perturbation attacks, while Aswomts achieves reliable model attribution, surpassing traditional similarity metrics like cosine similarity and SSIM. Together, these strategies provide a scalable and robust solution for diffusion-model traceability, advancing both image- and model-level provenance analysis. Physical sciences/Engineering Physical sciences/Mathematics and computing Image traceability Diffusion models Image fingerprints Model fingerprints Provenance analysis Robustness Graph neural networks 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-8404442","acceptedTermsAndConditions":true,"allowDirectSubmit":true,"archivedVersions":[],"articleType":"Article","associatedPublications":[],"authors":[{"id":592139483,"identity":"b95715dc-bec4-4edf-aaea-13375f1d0765","order_by":0,"name":"Guomin Gu","email":"","orcid":"","institution":"Zhejiang University of Technology","correspondingAuthor":false,"prefix":"","firstName":"Guomin","middleName":"","lastName":"Gu","suffix":""},{"id":592139484,"identity":"6cddef36-be50-45ec-bf31-1ffdd59755c1","order_by":1,"name":"Jintao Yu","email":"","orcid":"","institution":"Zhejiang University of Technology","correspondingAuthor":false,"prefix":"","firstName":"Jintao","middleName":"","lastName":"Yu","suffix":""},{"id":592139485,"identity":"ddc79f79-3f8f-4d4c-8b81-d9a2e467b092","order_by":2,"name":"Xiaojuan Wang","email":"","orcid":"","institution":"Zhejiang University of Technology","correspondingAuthor":false,"prefix":"","firstName":"Xiaojuan","middleName":"","lastName":"Wang","suffix":""},{"id":592139486,"identity":"c763a1e7-df4e-4210-8d54-f5f648e88fde","order_by":3,"name":"Haibing Zheng","email":"","orcid":"","institution":"Zhejiang University of Technology","correspondingAuthor":false,"prefix":"","firstName":"Haibing","middleName":"","lastName":"Zheng","suffix":""},{"id":592139487,"identity":"b42b8c4a-80ac-4e92-8f74-fc02792beb3d","order_by":4,"name":"Jinyin Chen","email":"data:image/png;base64,iVBORw0KGgoAAAANSUhEUgAAAZAAAAAyAQMAAABI0h/eAAAABlBMVEX///8AAABVwtN+AAAACXBIWXMAAA7EAAAOxAGVKw4bAAAA7ElEQVRIiWNgGAWjYDACCRA2YGBgY2A+AOYwMCQQrYUtAcgxIFILBPCAlBOhhX9287EHFgV3Evukez5/sGz7w8DPnmPA8HMHHkvuHEs3kDB4ltgmc3aDgWSbAYNkzxsDxt4zuLUYSOSYSUgYHE5sk8jdkADSYnAjx4CZsQ2flvxvUC05Dw6AtNgT1pLDBtPC2AC2RYKAFokbaWCHGbdJpBkzSJwz5pE486zgYC8eLfwzkp9JS/w5LDt/RvLjzxJlcnL87ckbH/zEowUEmIFx49gAZfCARA7g18DAwPiBgcEexhgFo2AUjIJRgAEAZ7BJ5vA8NbUAAAAASUVORK5CYII=","orcid":"","institution":"Zhejiang University of Technology","correspondingAuthor":true,"prefix":"","firstName":"Jinyin","middleName":"","lastName":"Chen","suffix":""},{"id":592139488,"identity":"78470120-8434-4bf0-a740-49c3732aa753","order_by":5,"name":"Baiyang Ji","email":"","orcid":"","institution":"Zhejiang University of Technology","correspondingAuthor":false,"prefix":"","firstName":"Baiyang","middleName":"","lastName":"Ji","suffix":""}],"badges":[],"createdAt":"2025-12-19 11:53:40","currentVersionCode":1,"declarations":"","doi":"10.21203/rs.3.rs-8404442/v1","doiUrl":"https://doi.org/10.21203/rs.3.rs-8404442/v1","draftVersion":[],"editorialEvents":[],"editorialNote":"","failedWorkflow":false,"files":[{"id":106098395,"identity":"58f9d14b-d0e8-481e-93bf-473b856323b0","added_by":"auto","created_at":"2026-04-03 12:02:49","extension":"pdf","order_by":1,"title":"","display":"","copyAsset":false,"role":"manuscript-pdf","size":586289,"visible":true,"origin":"","legend":"","description":"","filename":"journal1.pdf","url":"https://assets-eu.researchsquare.com/files/rs-8404442/v1_covered_9754f004-b15b-4eaa-a9e2-cfb728b272c7.pdf"}],"financialInterests":"No competing interests reported.","formattedTitle":"A Unified Traceability Framework for Diffusion Model Generated Images","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":"Image traceability, Diffusion models, Image fingerprints, Model fingerprints, Provenance analysis, Robustness, Graph neural networks","lastPublishedDoi":"10.21203/rs.3.rs-8404442/v1","lastPublishedDoiUrl":"https://doi.org/10.21203/rs.3.rs-8404442/v1","license":{"name":"CC BY 4.0","url":"https://creativecommons.org/licenses/by/4.0/"},"manuscriptAbstract":"Nowadays, diffusion models have become dominant generative tools capable of producing highly realistic images, while triggering new challenges for image provenance verification. Traditional content-based and metadata-based traceability methods fail to reliably distinguish synthetic from authentic images, while existing learning-based approaches face scalability and robustness limitations. To bridge the gap, we propose a novel unified traceability framework that integrates two complementary strategies: Arcits and Aswomts. Specifically, Arcits targets image-level provenance by exploiting reconstruction residuals as image fingerprints and combining them with lightweight model fingerprints extracted from the U-Net architecture. Aswomts extends to model-level provenance by encoding structural and weight information of diffusion models via graph neural networks and weighted similarity modeling, enabling the quantification of model similarity. Comprehensive experiments on multiple datasets demonstrate that Arcits outperforms baseline methods such as PRNU, KNN, ResNet50, and VGG16 in accuracy and robustness against perturbation attacks, while Aswomts achieves reliable model attribution, surpassing traditional similarity metrics like cosine similarity and SSIM. Together, these strategies provide a scalable and robust solution for diffusion-model traceability, advancing both image- and model-level provenance analysis.","manuscriptTitle":"A Unified Traceability Framework for Diffusion Model Generated Images","msid":"","msnumber":"","nonDraftVersions":[{"code":1,"date":"2026-02-18 09:47:56","doi":"10.21203/rs.3.rs-8404442/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":"fe857b5a-47b3-4554-9d45-da6bc61cd107","owner":[],"postedDate":"February 18th, 2026","published":true,"recentEditorialEvents":[],"rejectedJournal":[],"revision":"","amendment":"","status":"posted","subjectAreas":[{"id":63008473,"name":"Physical sciences/Engineering"},{"id":63008474,"name":"Physical sciences/Mathematics and computing"}],"tags":[],"updatedAt":"2026-04-03T11:59:08+00:00","versionOfRecord":[],"versionCreatedAt":"2026-02-18 09:47:56","video":"","vorDoi":"","vorDoiUrl":"","workflowStages":[]},"version":"v1","identity":"rs-8404442","journalConfig":"researchsquare"},"__N_SSP":true},"page":"/article/[identity]/[[...version]]","query":{"redirect":"/article/rs-8404442","identity":"rs-8404442","version":["v1"]},"buildId":"XKTyCvWXoU3ODBz1xrDgd","isFallback":false,"isExperimentalCompile":false,"dynamicIds":[84888],"gssp":true,"scriptLoader":[]}