STAR-Net: Spatio-Temporal Invertible Network for Video Watermarking against Composite Attacks

STAR-Net: Spatio-Temporal Invertible Network for Video Watermarking against Composite Attacks | 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 STAR-Net: Spatio-Temporal Invertible Network for Video Watermarking against Composite Attacks Qianhui Xu, Ke Niu This is a preprint; it has not been peer reviewed by a journal. https://doi.org/ 10.21203/rs.3.rs-9431864/v1 This work is licensed under a CC BY 4.0 License Status: Under Review Version 1 posted 13 You are reading this latest preprint version Abstract Video watermarking is crucial for digital media copyright protection. Existing invertible neural network (INN)-based methods predominantly rely on passive zero-padding to compensate for missing latent variables during extraction, which often leads to significant performance degradation under real-world composite attacks due to the irreversible loss of high-frequency information. To address this, we propose STAR-Net, a framework that shifts the paradigm from passive filling to active spatio-temporal prior reconstruction. Our approach introduces a Texture-Consistent Semantic Embedding (TCSE) module to project discrete watermark bits into a spatial representation aligned with the host video's high-frequency wavelet subbands, thereby enhancing embedding invisibility and mitigating semantic mismatch. Furthermore, to overcome the bottleneck of blind extraction, we design a Spatio-Temporal Selective-Kernel Latent Predictor (ST-SKLP) equipped with a multi-scale mechanism to actively reconstruct missing high-frequency residual priors from degraded videos. To bolster robustness, we construct a composite attack layer integrating a Gradient-Aware Perturbation Engine (GAPE) and a Differentiable High-Frequency Quantization Surrogate (DHQS). The GAPE generates adversarial noise tailored to maximize extraction error, simulating severe channel distortions. Extensive experiments on UCF-101 and Kinetics-600 demonstrate that STAR-Net achieves superior robustness and visual quality, effectively reconciling the trade-off between imperceptibility and extraction accuracy even under extreme compression. Video Watermarking Invertible Neural Network (INN) Robustness Composite Attacks Spatio-temporal Adaptive Full Text Additional Declarations No competing interests reported. Cite Share Download PDF Status: Under Review Version 1 posted Editorial decision: Revision requested 01 May, 2026 Reviews received at journal 29 Apr, 2026 Reviews received at journal 28 Apr, 2026 Reviews received at journal 25 Apr, 2026 Reviews received at journal 22 Apr, 2026 Reviewers agreed at journal 22 Apr, 2026 Reviewers agreed at journal 21 Apr, 2026 Reviewers agreed at journal 21 Apr, 2026 Reviewers agreed at journal 21 Apr, 2026 Reviewers invited by journal 21 Apr, 2026 Editor assigned by journal 16 Apr, 2026 Submission checks completed at journal 16 Apr, 2026 First submitted to journal 15 Apr, 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-9431864","acceptedTermsAndConditions":true,"allowDirectSubmit":false,"archivedVersions":[],"articleType":"Research Article","associatedPublications":[],"authors":[{"id":631207588,"identity":"d5f6cc92-32fe-4c4e-9d9f-85536800d446","order_by":0,"name":"Qianhui Xu","email":"data:image/png;base64,iVBORw0KGgoAAAANSUhEUgAAAZAAAAAyAQMAAABI0h/eAAAABlBMVEX///8AAABVwtN+AAAACXBIWXMAAA7EAAAOxAGVKw4bAAAA60lEQVRIiWNgGAWjYFAC5gMHEgwYeBhAKKFCQk6esBa2xAcfKmBazlgYGzYQ1MJjbDjjDJjBwMDYVpHIcICABoMbCWbSvG3WMvyze49JPJwnkcDYwPzw0Q08WiRnJKQBtaTzSNw5lyaRuE0ij52Bzdg4B48WfomEY0Ath3kYbuSYgbQUMzbwsEnj08ImkdgG1iIP1jJHIrHhAAEt/BLJzEDvH+YxAGtpIEKLZM8zRmAgp/MY3sgxtkg4JmFs2EzALwbH8z8Ao9LaXu5GjuHNHzV1cvLszQ8f49MCBcw42ERqGQWjYBSMglGABgCDz0ispnPB2QAAAABJRU5ErkJggg==","orcid":"","institution":"College of Cryptography Engineering, Engineering University of PAP","correspondingAuthor":true,"prefix":"","firstName":"Qianhui","middleName":"","lastName":"Xu","suffix":""},{"id":631207589,"identity":"f33197ae-ee6d-4619-af19-0aa5f75413f9","order_by":1,"name":"Ke Niu","email":"","orcid":"","institution":"College of Cryptography Engineering, Engineering University of PAP","correspondingAuthor":false,"prefix":"","firstName":"Ke","middleName":"","lastName":"Niu","suffix":""}],"badges":[],"createdAt":"2026-04-16 01:38:36","currentVersionCode":1,"declarations":"","doi":"10.21203/rs.3.rs-9431864/v1","doiUrl":"https://doi.org/10.21203/rs.3.rs-9431864/v1","draftVersion":[],"editorialEvents":[],"editorialNote":"","failedWorkflow":false,"files":[{"id":108183094,"identity":"a6179a70-ed92-4184-bbfd-93b28dace0b6","added_by":"auto","created_at":"2026-04-30 08:59:47","extension":"pdf","order_by":1,"title":"","display":"","copyAsset":false,"role":"manuscript-pdf","size":3402701,"visible":true,"origin":"","legend":"","description":"","filename":"STARNet.pdf","url":"https://assets-eu.researchsquare.com/files/rs-9431864/v1_covered_9230c11c-197b-44c5-9243-b56506306f6c.pdf"}],"financialInterests":"No competing interests reported.","formattedTitle":"STAR-Net: Spatio-Temporal Invertible Network for Video Watermarking against Composite Attacks","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":"journal-of-king-saud-university-computer-and-information-sciences","isNatureJournal":false,"hasQc":true,"allowDirectSubmit":false,"externalIdentity":"","sideBox":"Learn more about [Journal of King Saud University Computer and Information Sciences](https://link.springer.com/journal/44443)","snPcode":"44443","submissionUrl":"https://submission.springernature.com/new-submission/44443/3","title":"Journal of King Saud University Computer and Information Sciences","twitterHandle":"","acdcEnabled":true,"dfaEnabled":true,"editorialSystem":"stoa","reportingPortfolio":"Springer Open","inReviewEnabled":true,"inReviewRevisionsEnabled":true},"keywords":"Video Watermarking, Invertible Neural Network (INN), Robustness, Composite Attacks, Spatio-temporal Adaptive","lastPublishedDoi":"10.21203/rs.3.rs-9431864/v1","lastPublishedDoiUrl":"https://doi.org/10.21203/rs.3.rs-9431864/v1","license":{"name":"CC BY 4.0","url":"https://creativecommons.org/licenses/by/4.0/"},"manuscriptAbstract":"\u003cp\u003eVideo watermarking is crucial for digital media copyright protection. Existing invertible neural network (INN)-based methods predominantly rely on passive zero-padding to compensate for missing latent variables during extraction, which often leads to significant performance degradation under real-world composite attacks due to the irreversible loss of high-frequency information. To address this, we propose STAR-Net, a framework that shifts the paradigm from passive filling to active spatio-temporal prior reconstruction. Our approach introduces a Texture-Consistent Semantic Embedding (TCSE) module to project discrete watermark bits into a spatial representation aligned with the host video's high-frequency wavelet subbands, thereby enhancing embedding invisibility and mitigating semantic mismatch. Furthermore, to overcome the bottleneck of blind extraction, we design a Spatio-Temporal Selective-Kernel Latent Predictor (ST-SKLP) equipped with a multi-scale mechanism to actively reconstruct missing high-frequency residual priors from degraded videos. To bolster robustness, we construct a composite attack layer integrating a Gradient-Aware Perturbation Engine (GAPE) and a Differentiable High-Frequency Quantization Surrogate (DHQS). The GAPE generates adversarial noise tailored to maximize extraction error, simulating severe channel distortions. Extensive experiments on UCF-101 and Kinetics-600 demonstrate that STAR-Net achieves superior robustness and visual quality, effectively reconciling the trade-off between imperceptibility and extraction accuracy even under extreme compression.\u003c/p\u003e","manuscriptTitle":"STAR-Net: Spatio-Temporal Invertible Network for Video Watermarking against Composite Attacks","msid":"","msnumber":"","nonDraftVersions":[{"code":1,"date":"2026-04-29 16:39:55","doi":"10.21203/rs.3.rs-9431864/v1","editorialEvents":[{"type":"communityComments","content":0},{"type":"decision","content":"Revision requested","date":"2026-05-01T12:19:27+00:00","index":"","fulltext":""},{"type":"editorInvitedReview","content":"","date":"2026-04-29T17:11:25+00:00","index":"hide","fulltext":""},{"type":"editorInvitedReview","content":"","date":"2026-04-28T15:46:36+00:00","index":"hide","fulltext":""},{"type":"editorInvitedReview","content":"","date":"2026-04-25T11:24:49+00:00","index":"hide","fulltext":""},{"type":"editorInvitedReview","content":"","date":"2026-04-22T16:09:43+00:00","index":"hide","fulltext":""},{"type":"reviewerAgreed","content":"231913494159878522499875811455332803342","date":"2026-04-22T05:57:11+00:00","index":"hide","fulltext":""},{"type":"reviewerAgreed","content":"43396106917392216582821702599872316604","date":"2026-04-21T13:32:59+00:00","index":"hide","fulltext":""},{"type":"reviewerAgreed","content":"247225509078836970500856808794817884631","date":"2026-04-21T13:00:36+00:00","index":"hide","fulltext":""},{"type":"reviewerAgreed","content":"47012587147981223330513248633847392040","date":"2026-04-21T07:24:56+00:00","index":"hide","fulltext":""},{"type":"reviewersInvited","content":"","date":"2026-04-21T07:08:54+00:00","index":"","fulltext":""},{"type":"editorAssigned","content":"","date":"2026-04-16T11:56:58+00:00","index":"","fulltext":""},{"type":"checksComplete","content":"","date":"2026-04-16T11:56:21+00:00","index":"","fulltext":""},{"type":"submitted","content":"Journal of King Saud University Computer and Information Sciences","date":"2026-04-16T01:34:54+00:00","index":"","fulltext":""}],"status":"published","journal":{"display":true,"email":"[email protected]","identity":"journal-of-king-saud-university-computer-and-information-sciences","isNatureJournal":false,"hasQc":true,"allowDirectSubmit":false,"externalIdentity":"","sideBox":"Learn more about [Journal of King Saud University Computer and Information Sciences](https://link.springer.com/journal/44443)","snPcode":"44443","submissionUrl":"https://submission.springernature.com/new-submission/44443/3","title":"Journal of King Saud University Computer and Information Sciences","twitterHandle":"","acdcEnabled":true,"dfaEnabled":true,"editorialSystem":"stoa","reportingPortfolio":"Springer Open","inReviewEnabled":true,"inReviewRevisionsEnabled":true}}],"origin":"","ownerIdentity":"8e34f522-487b-4e73-a11e-4e7fdb8d3d2f","owner":[],"postedDate":"April 29th, 2026","published":true,"recentEditorialEvents":[{"type":"decision","content":"Revision requested","date":"2026-05-01T12:19:27+00:00","index":"","fulltext":""},{"type":"editorInvitedReview","content":"","date":"2026-04-29T17:11:25+00:00","index":47,"fulltext":""}],"rejectedJournal":[],"revision":"","amendment":"","status":"under-review","subjectAreas":[],"tags":[],"updatedAt":"2026-05-09T03:38:57+00:00","versionOfRecord":[],"versionCreatedAt":"2026-04-29 16:39:55","video":"","vorDoi":"","vorDoiUrl":"","workflowStages":[]},"version":"v1","identity":"rs-9431864","journalConfig":"researchsquare"},"__N_SSP":true},"page":"/article/[identity]/[[...version]]","query":{"redirect":"/article/rs-9431864","identity":"rs-9431864","version":["v1"]},"buildId":"XKTyCvWXoU3ODBz1xrDgd","isFallback":false,"isExperimentalCompile":false,"dynamicIds":[84888],"gssp":true,"scriptLoader":[]}