Robust Image Watermarking Based on Generative Adversarial Networks for Copyright Protection

Robust Image Watermarking Based on Generative Adversarial Networks for Copyright Protection | 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 Robust Image Watermarking Based on Generative Adversarial Networks for Copyright Protection Guangyong Gao, Tianyou Xu, Feng Hua This is a preprint; it has not been peer reviewed by a journal. https://doi.org/ 10.21203/rs.3.rs-4039149/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 Digital media is easy to be copied, which leads to a proliferation of copyright infringement. One proposed solution is digital watermarking technology, which is to embed message bits into multimedia carriers such as images and videos to prove the creator’s ownership of his work. Most recently, with the upsurge of convolutional neural network in the terms of artificial intelligence, deep learning has made great achievements in digital watermarking. In this work, we propose a new framework with robust image watermarking based on a generative adversarial network (RIW-GAN). With proposed method, the encoder network is composed of convolutional layers and a residual block outputs the encoded image that has low distortion and is closer to the original image. To enhance the robustness to attack of the model, a simulated noise layer as a differentiable network layer is applied to promote end-to-end training before decoding. Therefore, the proposed model has higher accuracy rate for decoding the attacked encoded image. In comparison to the state-of-the-art model, the experimental results demonstrate that RIW-GAN has superior invisibility and stronger robustness against regular attacks like JPEG compression and geometric attacks such as resizing and cropping. Robust Image Watermarking Deep Learning Adversarial Training Generative Adversarial Network Copyright Protection. 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-4039149","acceptedTermsAndConditions":true,"allowDirectSubmit":true,"archivedVersions":[],"articleType":"Research Article","associatedPublications":[],"authors":[{"id":278032513,"identity":"4c052da4-8f8a-42fd-8929-47ffb2cc8bb6","order_by":0,"name":"Guangyong Gao","email":"data:image/png;base64,iVBORw0KGgoAAAANSUhEUgAAAZAAAAAyAQMAAABI0h/eAAAABlBMVEX///8AAABVwtN+AAAACXBIWXMAAA7EAAAOxAGVKw4bAAAA40lEQVRIiWNgGAWjYNCDDwY2dqTpYJxRkJZMmhZmng+HGBsIqZJ3P3z4NU/NHbsNx3sPv7YxOMDMwH746AZ8WgzPpKVZ8xx7lrzhzLk06xyDO3wMPGlpN/BqacgxM+ZhO5xscAPIyDF4xswgwWOGX0v/G6CWf1AtFgaHGRsIaZGXyDF+zNt22A6oxfgxAzFaDCSepTHO7TucIHnmjBljj0FaMhshv8j3Jx/+8ObbYXu+4z3GH378sbHjZz98DL8tBxjYJIB04gIog4ENn3KwLQ0MzB+AtD2MMQpGwSgYBaMAAwAAEfhQxLuOB4wAAAAASUVORK5CYII=","orcid":"","institution":"Nanjing University of Information Science \u0026 Technology","correspondingAuthor":true,"prefix":"","firstName":"Guangyong","middleName":"","lastName":"Gao","suffix":""},{"id":278032514,"identity":"05e7513f-971e-4cca-84aa-b14b71f375d1","order_by":1,"name":"Tianyou Xu","email":"","orcid":"","institution":"Nanjing University of Information Science \u0026 Technology","correspondingAuthor":false,"prefix":"","firstName":"Tianyou","middleName":"","lastName":"Xu","suffix":""},{"id":278032515,"identity":"b3f2edbd-9059-4358-ba62-cd34438c2c10","order_by":2,"name":"Feng Hua","email":"","orcid":"","institution":"Nanjing University of Information Science \u0026 Technology","correspondingAuthor":false,"prefix":"","firstName":"Feng","middleName":"","lastName":"Hua","suffix":""}],"badges":[],"createdAt":"2024-03-08 07:47:33","currentVersionCode":1,"declarations":"","doi":"10.21203/rs.3.rs-4039149/v1","doiUrl":"https://doi.org/10.21203/rs.3.rs-4039149/v1","draftVersion":[],"editorialEvents":[],"editorialNote":"","failedWorkflow":false,"files":[{"id":64171149,"identity":"a31718a4-dcb9-44d6-a6c9-eb84d860fd8e","added_by":"auto","created_at":"2024-09-09 11:02:29","extension":"pdf","order_by":1,"title":"","display":"","copyAsset":false,"role":"manuscript-pdf","size":1360526,"visible":true,"origin":"","legend":"","description":"","filename":"RobustImageWatermarkingBasedonGenerativeAdversarialNetworksforCopyrightProtection.pdf","url":"https://assets-eu.researchsquare.com/files/rs-4039149/v1_covered_1699b3eb-c849-459f-b4b3-ee874887721f.pdf"}],"financialInterests":"No competing interests reported.","formattedTitle":"Robust Image Watermarking Based on Generative Adversarial Networks for Copyright Protection","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":"Robust Image Watermarking, Deep Learning, Adversarial Training, Generative Adversarial Network, Copyright Protection.","lastPublishedDoi":"10.21203/rs.3.rs-4039149/v1","lastPublishedDoiUrl":"https://doi.org/10.21203/rs.3.rs-4039149/v1","license":{"name":"CC BY 4.0","url":"https://creativecommons.org/licenses/by/4.0/"},"manuscriptAbstract":"Digital media is easy to be copied, which leads to a proliferation of copyright infringement. One proposed solution is digital watermarking technology, which is to embed message bits into multimedia carriers such as images and videos to prove the creator’s ownership of his work. Most recently, with the upsurge of convolutional neural network in the terms of artificial intelligence, deep learning has made great achievements in digital watermarking. In this work, we propose a new framework with robust image watermarking based on a generative adversarial network (RIW-GAN). With proposed method, the encoder network is composed of convolutional layers and a residual block outputs the encoded image that has low distortion and is closer to the original image. To enhance the robustness to attack of the model, a simulated noise layer as a differentiable network layer is applied to promote end-to-end training before decoding. Therefore, the proposed model has higher accuracy rate for decoding the attacked encoded image. In comparison to the state-of-the-art model, the experimental results demonstrate that RIW-GAN has superior invisibility and stronger robustness against regular attacks like JPEG compression and geometric attacks such as resizing and cropping.","manuscriptTitle":"Robust Image Watermarking Based on Generative Adversarial Networks for Copyright Protection","msid":"","msnumber":"","nonDraftVersions":[{"code":1,"date":"2024-03-12 13:31:54","doi":"10.21203/rs.3.rs-4039149/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":"00cb2efa-ba1b-4b2c-88cb-81a4a584c4a7","owner":[],"postedDate":"March 12th, 2024","published":true,"recentEditorialEvents":[],"rejectedJournal":[],"revision":"","amendment":"","status":"posted","subjectAreas":[],"tags":[],"updatedAt":"2024-09-09T10:54:21+00:00","versionOfRecord":[],"versionCreatedAt":"2024-03-12 13:31:54","video":"","vorDoi":"","vorDoiUrl":"","workflowStages":[]},"version":"v1","identity":"rs-4039149","journalConfig":"researchsquare"},"__N_SSP":true},"page":"/article/[identity]/[[...version]]","query":{"redirect":"/article/rs-4039149","identity":"rs-4039149","version":["v1"]},"buildId":"qtupq5eGEP_6zYnWcrvyt","isFallback":false,"isExperimentalCompile":false,"dynamicIds":[84888],"gssp":true,"scriptLoader":[]}