[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"doc-detail-82141-en":3,"doc-seo-82141-105":29,"detail-sidebar-cat-0-en-105":91},{"code":4,"msg":5,"data":6},0,"success",{"doc_id":7,"user_id":8,"nickname":9,"user_avatar":10,"doc_module":4,"category_id":11,"category_name":12,"doc_title":13,"doc_description":14,"doc_content":15,"file_id":16,"file_url":17,"file_type":18,"file_size":19,"view_count":20,"is_deleted":4,"is_public":20,"is_downloadable":20,"audit_status":20,"page_count":21,"language":22,"language_code":23,"site_id":24,"html_lang":23,"table_of_contents":25,"faqs":26,"seo_title":13,"seo_description":14,"update_tm":27,"read_time":28},82141,1099514067438,"River Wang","https://ap-avatar.wpscdn.com/avatar/100002539ee87300030?x-image-process=image/resize,m_fixed,w_180,h_180&k=1780474512215547542",8,"Research & Report","RaMark: Radioactive Watermarking for Generated Tabular Data","Recent advances in generative modeling make generated tabular data a practical approach for privacy-sensitive data sharing, where watermarking supports ownership verification. Existing methods fail against retraining attacks, where an adversary retrains a generative model on a watermarked dataset and regenerates high-utility data that no longer carries the watermark. RaMark introduces “radioactivity,” ensuring watermark detectability after retraining by embedding a sinusoidal dependency into the intrinsic data distribution. Theory and experiments show utility degradation when removal occurs and stronger robustness than state-of-the-art methods under large-scale verification.","RaMark: Radioactive Watermarking for Generated Tabular Data  \nXin Che  \nMcMaster University Hamilton, Canada [chex5@mcmaster.ca](chex5@mcmaster.ca)  \nXinyu Ma  \nMcMaster University Hamilton, Canada [ma209@mcmaster.ca](ma209@mcmaster.ca)  \nLingyang Chu McMaster University  \nHamilton, Canada [chul9@mcmaster.ca](chul9@mcmaster.ca)  \nXuan Luo  \nYork University Toronto, Canada [xuanluo@yorku.ca](xuanluo@yorku.ca)  \nQiqi Zhang  \nMcMaster University Hamilton, Canada [zhangq16@mcmaster.ca](zhangq16@mcmaster.ca)  \nJian Pei  \nDuke University Durham, United States [j.pei@duke.edu](j.pei@duke.edu)  \narXiv :2607 .09000v 1 [ cs .CR] 10 Jul 2026  \nAbstract  \nRecent advances in generative modeling have made generated tabular data a practical solution for privacy-sensitive data sharing, where watermarking enables ownership verification. However, existing watermarking methods fundamentally fail under retraining attacks, in which an adversary retrains a generative model on a watermarked dataset and regenerates high-utility data that no longer carries the watermark. We address this challenge by introducing radioactivity, the property that a watermark remains detectable after generative model retraining, and propose RaMark, a radioactive watermarking method that embeds a sinusoidal dependency asan intrinsic component of the data distribution. By coupling the watermark with the underlying distribution, RaMark ensures that any generative model preserving data utility also has to preserve the watermark. We theoretically show that with high probability removing watermark degrades utility and alters data distribution. Extensive experiments on two real-world tabular datasets, under a large-scale ownership verification setting with 105 independent data owners, demonstrate that RaMark achieves substantially stronger radioactivity than seven state-of-the-art methods and consistently outperforms them against both retraining and data modification attacks.  \nCCS Concepts  \n• Do Not Use This Code → Generate the Correct Terms for Your Paper; Generate the Correct Terms for Your Paper; Generate the Correct Terms for Your Paper; Generate the Correct Terms for Your Paper.  \nKeywords  \nRadioactive watermark, retraining attack, generated tabular data  \nACM Reference Format:  \nXin Che, Lingyang Chu, Qiqi Zhang, Xinyu Ma, Xuan Luo, and Jian Pei.  \n2018. RaMark: Radioactive Watermarking for Generated Tabular Data. In Proceedings of Make sure to enter the correct conference title from your rights  \nPermission to make digital or hard copies of all or part of this work for personal or classroom use is granted without fee provided that copies are not made or distributed for profit or commercial advantage and that copies bear this notice and the full citation on the first page. Copyrights for components of this work owned by others than the author(s) must be honored. Abstracting with credit is permitted. To copy otherwise, or republish, to post on servers or to redistribute to lists, requires prior specific permission [and/or a fee. Request permissions from permissions@acm.org](and/or a fee. Request permissions from permissions@acm.org).  \nConference acronym ’XX, Woodstock, NY  \n© 2018 Copyright held by the owner/author(s) . Publication rights licensed to ACM. ACM ISBN 978-1-4503-XXXX-X/2018/06  \n[https://doi.org/XXXXXXX.XXXXXXX](https://doi.org/XXXXXXX.XXXXXXX)  \nFigure 1: Illustration of retraining attack and radioactive watermark. The data owner trains a generative model on the original dataset and samples a watermarked dataset that carries a radioactive watermark. An adversary performs aretraining attack by training a new generative model on the watermarked dataset and sampling a regenerated dataset. Because the watermark is radioactive, it remains detectable in the regenerated dataset despite retraining.  \nconfirmation email (Conference acronym ’XX). ACM, New York, NY, USA, 20 pages. [https://doi.org/XXXXXXX.XXXXXXX](https://doi.org/XXXXXXX.XXXXXXX)  \n1 Introduction  \nR","cbCaihH8QUGg7wZ0","https://ap.wps.com/l/cbCaihH8QUGg7wZ0","pdf",1389228,1,20,"English","en",105,"# Abstract\n# Introduction","[{\"question\":\"What problem does RaMark address in generated tabular data watermarking?\",\"answer\":\"RaMark addresses the failure of existing watermarking methods under retraining attacks, where an adversary retrains a generative model on a watermarked dataset and regenerates data that no longer contains the watermark.\"},{\"question\":\"How does RaMark make a watermark detectable after retraining?\",\"answer\":\"RaMark introduces “radioactivity” by embedding a sinusoidal dependency as an intrinsic component of the data distribution, coupling the watermark with the underlying distribution so that utility-preserving generation must preserve the watermark.\"},{\"question\":\"What do the theoretical and experimental results show about removing the watermark?\",\"answer\":\"Theoretical results indicate that removing the watermark degrades utility and alters the data distribution with high probability. Experiments on two real-world tabular datasets further show RaMark achieves substantially stronger radioactivity and consistently outperforms prior methods against retraining and data modification attacks.\"}]",1784178415,50,{"code":4,"msg":30,"data":31},"ok",{"site_id":24,"language":23,"slug":32,"title":13,"keywords":33,"description":14,"schema_data":34,"social_meta":86,"head_meta":88,"extra_data":90,"updated_unix":27},"ramark-radioactive-watermarking-for-generated-tabular-data","",{"@graph":35,"@context":85},[36,53,68],{"@type":37,"itemListElement":38},"BreadcrumbList",[39,43,47,50],{"item":40,"name":41,"@type":42,"position":20},"https://docshare.wps.com","Home","ListItem",{"item":44,"name":45,"@type":42,"position":46},"https://docshare.wps.com/document/","Document",2,{"item":48,"name":12,"@type":42,"position":49},"https://docshare.wps.com/document/research-report/",3,{"item":51,"name":13,"@type":42,"position":52},"https://docshare.wps.com/document/ramark-radioactive-watermarking-for-generated-tabular-data/82141/",4,{"url":51,"name":13,"@type":54,"author":55,"headline":13,"publisher":57,"fileFormat":60,"inLanguage":23,"description":14,"dateModified":61,"datePublished":62,"encodingFormat":60,"isAccessibleForFree":63,"interactionStatistic":64},"DigitalDocument",{"name":9,"@type":56},"Person",{"url":40,"name":58,"@type":59},"DocShare","Organization","application/pdf","2026-07-17","2026-07-16",true,{"@type":65,"interactionType":66,"userInteractionCount":20},"InteractionCounter",{"@type":67},"ViewAction",{"@type":69,"mainEntity":70},"FAQPage",[71,77,81],{"name":72,"@type":73,"acceptedAnswer":74},"What problem does RaMark address in generated tabular data watermarking?","Question",{"text":75,"@type":76},"RaMark addresses the failure of existing watermarking methods under retraining attacks, where an adversary retrains a generative model on a watermarked dataset and regenerates data that no longer contains the watermark.","Answer",{"name":78,"@type":73,"acceptedAnswer":79},"How does RaMark make a watermark detectable after retraining?",{"text":80,"@type":76},"RaMark introduces “radioactivity” by embedding a sinusoidal dependency as an intrinsic component of the data distribution, coupling the watermark with the underlying distribution so that utility-preserving generation must preserve the watermark.",{"name":82,"@type":73,"acceptedAnswer":83},"What do the theoretical and experimental results show about removing the watermark?",{"text":84,"@type":76},"Theoretical results indicate that removing the watermark degrades utility and alters the data distribution with high probability. Experiments on two real-world tabular datasets further show RaMark achieves substantially stronger radioactivity and consistently outperforms prior methods against retraining and data modification attacks.","https://schema.org",{"og:url":51,"og:type":87,"og:title":13,"og:site_name":58,"og:description":14},"article",{"robots":89,"canonical":51},"index,follow",{"doc_id":7,"site_id":24},{"code":4,"msg":5,"data":92},[93,97,101,105,110,114,119,122,126,129,133],{"id":20,"doc_module":4,"doc_module_name":45,"category_name":94,"show_sort_weight":95,"slug":96},"Story & Novel",90,"story-novel",{"id":46,"doc_module":4,"doc_module_name":45,"category_name":98,"show_sort_weight":99,"slug":100},"Literature",80,"literature",{"id":52,"doc_module":4,"doc_module_name":45,"category_name":102,"show_sort_weight":103,"slug":104},"Exam",70,"exam",{"id":106,"doc_module":4,"doc_module_name":45,"category_name":107,"show_sort_weight":108,"slug":109},5,"Comic",60,"comic",{"id":111,"doc_module":4,"doc_module_name":45,"category_name":112,"show_sort_weight":28,"slug":113},6,"Technology","technology",{"id":115,"doc_module":4,"doc_module_name":45,"category_name":116,"show_sort_weight":117,"slug":118},7,"Healthcare",40,"healthcare",{"id":11,"doc_module":4,"doc_module_name":45,"category_name":12,"show_sort_weight":120,"slug":121},30,"research-report",{"id":123,"doc_module":4,"doc_module_name":45,"category_name":124,"show_sort_weight":21,"slug":125},9,"Religion & Spirituality","religion-spirituality",{"id":21,"doc_module":4,"doc_module_name":45,"category_name":127,"show_sort_weight":21,"slug":128},"World Cup","world-cup",{"id":130,"doc_module":4,"doc_module_name":45,"category_name":131,"show_sort_weight":130,"slug":132},10,"Lifestyle","lifestyle",{"id":134,"doc_module":4,"doc_module_name":45,"category_name":135,"show_sort_weight":106,"slug":136},19,"General","general"]