[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"doc-detail-118914-en":3,"doc-seo-118914-105":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":11,"language":21,"language_code":22,"site_id":23,"html_lang":22,"table_of_contents":24,"faqs":25,"seo_title":26,"seo_description":14,"update_tm":27,"read_time":28},118914,1649267921044,"Ava Thompson","https://us-avatar.wpscdn.com/avatar/1800007509477c92dfb?_k=1782875107921204101",8,"Research & Report","ENHANCING MODEL SECURITY - LEVERAGING USER-GENERATED IDS AS EMBEDDED WATERMARKS IN MACHINE LEARNING MODELS","Machine learning model theft or unauthorized reuse can cause substantial financial losses and serious damage to a company’s intellectual property. Existing protections such as encryption or access controls can be bypassed by skilled adversaries. The document proposes embedding embedded watermarks directly into machine learning models, enabling unique model identification and user-level identification. If a model is leaked or misused, watermark extraction supports source traceability and accountability, and helps enable detection and prosecution of unauthorized use.","Technical Disclosure Commons  \nDefensive Publications Series  \nOctober 2023  \nENHANCING MODEL SECURITY: LEVERAGING USER-GENERATED IDS AS EMBEDDED WATERMARKS IN MACHINE LEARNING MODELS  \nAlan Gatzke  \nMitchell C Mosure  \nAndi Wilson  \nAnanth Racherla  \nTodd C Kuehnl  \nSee next page for additional authors  \nFollow this and additional works at: [https://www.tdcommons.org/dpubs_series](https://www.tdcommons.org/dpubs_series)  \nRecommended Citation  \nGatzke, Alan; C Mosure, Mitchell; Wilson, Andi; Racherla, Ananth; C Kuehnl, Todd; and McCarthy, Tyler Shane, \"ENHANCING MODEL SECURITY: LEVERAGING USER-GENERATED IDS AS EMBEDDED WATERMARKS IN MACHINE LEARNING MODELS\", Technical Disclosure Commons,(October 23, 2023)  \n[https://www.tdcommons.org/dpubs_series/6337](https://www.tdcommons.org/dpubs_series/6337)  \nThis work is licensed under a Creative Commons Attribution 4.0 License.  \nThis Article is brought to you for free and open access by Technical Disclosure Commons. It has been accepted for inclusion in Defensive Publications Series by an authorized administrator of Technical Disclosure Commons.  \nInventor(s)  \nAlan Gatzke, Mitchell C Mosure, Andi Wilson, Ananth Racherla, Todd C Kuehnl, and Tyler Shane McCarthy  \nThis article is available at Technical Disclosure Commons: [https://www.tdcommons.org/dpubs_series/6337](https://www.tdcommons.org/dpubs_series/6337)  \nENHANCING MODEL SECURITY: LEVERAGING USER-GENERATED IDS AS  \nEMBEDDED WATERMARKS IN MACHINE LEARNING MODELS  \nAUTHORS:  \nAlan Gatzke  \nMitchell C Mosure  \nAndi Wilson  \nAnanth Racherla  \nTodd C Kuehnl  \nTyler Shane McCarthy  \nABSTRACT  \nThe potential theft or unauthorized use of machine learning models developed by a company can lead to significant financial losses and damage to the company's intellectual property. While existing methods of protecting machine learning models such as encryption or access controls can be circumvented by skilled attacker, techniques presented herein involve the integration of embedded watermarks into machine learning models. Such techniques involving the integration of embedded watermarks may not only uniquely identify a model but may also include a unique user identification/identity that can make it possible to track usage of the model and detect any unauthorized use of the model. Thus, if a model is leaked, redistributed, or misused, the watermark for the model makes it possible to identify a source of the leak/misuse, allowing for better traceability and accountability.  \nDETAILED DESCRIPTION  \nProposed herein are techniques to address the potential theft or unauthorized use of machine learning models, which can lead to significant financial losses and damage to acompany's intellectual property. Many existing methods of protecting machine learning models, such as encryption or access controls, can be circumvented by skilled attackers. However, techniques presented herein involve the integration of embedded watermarks into machine learning models. These watermarks not only uniquely identify a model but can also include a unique user identification, enabling the tracking of model usage and detection of any unauthorized use. By implementing embedded watermarks with unique user identifications, the techniques proposed herein can significantly reduce the risk of  \n1 6966  \nPublished by Technical Disclosure Commons, 2023 2  \nintellectual property theft and also facilitate the detection and prosecution of any  \nunauthorized use.  \nIn accordance with techniques of this proposal, a watermarking system can inject user personalized watermarks in a model at runtime of the model. Broadly, operations of the watermarking system may include three high-level steps involving: 1) encoding a watermark, which is a unique identifier/identity (ID) tied to a specific user, into a form that can be hidden in the cover data of a model (e.g., a sparse pattern or algorithm could be used to change the watermark information into chosen parts of a model); 2) embedding the ","cbCairx2x2OObNtg","https://ap.wps.com/l/cbCairx2x2OObNtg","pdf",184244,1,"English","en",105,"# Abstract\n# Detailed Description\n## Threat and Limitations of Existing Protections\n## Embedded Watermarking Approach\n## Watermark Encoding, Embedding, and Recovery\n## Example UserID Watermarking Operations","[{\"question\":\"Why are traditional protections like encryption or access controls insufficient?\",\"answer\":\"They can be circumvented by skilled attackers, enabling theft or unauthorized use of machine learning models.\"},{\"question\":\"How do embedded watermarks help protect machine learning models?\",\"answer\":\"They uniquely identify a model and can include a user identity to track usage and detect unauthorized use.\"},{\"question\":\"What are the main steps of the proposed watermarking system?\",\"answer\":\"Encode a user-tied ID into a hidden form, embed it into selected model cover data (weights or biases) with minimal performance impact, then recover the ID by extracting the hidden watermark via decoding or a trained helper model.\"}]","ENHANCING MODEL SECURITY - LEVERAGING USER-GENERATED IDS AS EMBEDDED WATERMARKS IN MACHINE LEARNING MODELS | PDF",1785720928,20,{"code":4,"msg":30,"data":31},"ok",{"site_id":23,"language":22,"slug":32,"title":13,"keywords":33,"description":14,"schema_data":34,"social_meta":86,"head_meta":88,"extra_data":90,"updated_unix":27},"enhancing-model-security-leveraging-user-generated-ids-as-embedded-watermarks-in-machine-learning-models","",{"@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/enhancing-model-security-leveraging-user-generated-ids-as-embedded-watermarks-in-machine-learning-models/118914/",4,{"url":51,"name":13,"@type":54,"author":55,"headline":13,"publisher":57,"fileFormat":60,"inLanguage":22,"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","2026-08-05","2026-08-03",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},"Why are traditional protections like encryption or access controls insufficient?","Question",{"text":75,"@type":76},"They can be circumvented by skilled attackers, enabling theft or unauthorized use of machine learning models.","Answer",{"name":78,"@type":73,"acceptedAnswer":79},"How do embedded watermarks help protect machine learning models?",{"text":80,"@type":76},"They uniquely identify a model and can include a user identity to track usage and detect unauthorized use.",{"name":82,"@type":73,"acceptedAnswer":83},"What are the main steps of the proposed watermarking system?",{"text":84,"@type":76},"Encode a user-tied ID into a hidden form, embed it into selected model cover data (weights or biases) with minimal performance impact, then recover the ID by extracting the hidden watermark via decoding or a trained helper model.","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":23},{"code":4,"msg":5,"data":92},[93,97,101,105,110,115,120,123,127,130,134],{"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":113,"slug":114},6,"Technology",50,"technology",{"id":116,"doc_module":4,"doc_module_name":45,"category_name":117,"show_sort_weight":118,"slug":119},7,"Healthcare",40,"healthcare",{"id":11,"doc_module":4,"doc_module_name":45,"category_name":12,"show_sort_weight":121,"slug":122},30,"research-report",{"id":124,"doc_module":4,"doc_module_name":45,"category_name":125,"show_sort_weight":28,"slug":126},9,"Religion & Spirituality","religion-spirituality",{"id":28,"doc_module":4,"doc_module_name":45,"category_name":128,"show_sort_weight":28,"slug":129},"World Cup","world-cup",{"id":131,"doc_module":4,"doc_module_name":45,"category_name":132,"show_sort_weight":131,"slug":133},10,"Lifestyle","lifestyle",{"id":135,"doc_module":4,"doc_module_name":45,"category_name":136,"show_sort_weight":106,"slug":137},19,"General","general"]