{"about":{"non_affiliation":"Code with Papers and Syntology are not affiliated with, endorsed by, or sponsored by Papers with Code, Meta, or the pwc-archive mirror.","site":"https://codewithpapers.app","licence":"CC BY-SA 4.0","licence_url":"https://creativecommons.org/licenses/by-sa/4.0/legalcode","attribution":"https://codewithpapers.app/attribution","modified":"archive material modified by Syntology; see the attribution page","syntology":{"site":"https://syntology.ai","developers":"https://syntology.ai/developers","mcp":{"server":"https://syntology.ai/mcp","transport":"streamable-http","server_card":"https://syntology.ai/.well-known/mcp/server-card.json","auth":{"type":"trial token, no account","trial_token":"https://syntology.ai/api/oauth/trial/token","method":"POST","docs":"https://syntology.ai/developers"}},"have":"https://syntology.ai/api/graph/have?x=<method, arXiv id or title> (free, answers coverage only)","paper_base":"https://syntology.ai/paper/","atlas_base":"https://app.syntology.ai/?focus="},"machine_readable":[{"url":"https://codewithpapers.app/llms.txt","what":"the machine catalog: every machine-readable file, counted"},{"url":"https://codewithpapers.app/index/manifest.json","what":"paper-to-code index by arXiv id, with Syntology's counts"},{"url":"https://codewithpapers.app/search/manifest.json","what":"site search index (titles, authors) and its files"},{"url":"https://codewithpapers.app/download","what":"bulk files: Syntology's layer, described there"},{"url":"https://codewithpapers.app/build_manifest.json","what":"the build record: inputs, counts, exclusions, probes"}]},"url":"/paper/entangled-watermarks-as-a-defense-against","title":"Entangled Watermarks as a Defense against Model Extraction","arxiv_id":"2002.12200","date":"2020-02-27","proceeding":null,"authors":["Hengrui Jia","Christopher A. Choquette-Choo","Varun Chandrasekaran","Nicolas Papernot"],"abstract":"Machine learning involves expensive data collection and training procedures. Model owners may be concerned that valuable intellectual property can be leaked if adversaries mount model extraction attacks. As it is difficult to defend against model extraction without sacrificing significant prediction accuracy, watermarking instead leverages unused model capacity to have the model overfit to outlier input-output pairs. Such pairs are watermarks, which are not sampled from the task distribution and are only known to the defender. The defender then demonstrates knowledge of the input-output pairs to claim ownership of the model at inference. The effectiveness of watermarks remains limited because they are distinct from the task distribution and can thus be easily removed through compression or other forms of knowledge transfer. We introduce Entangled Watermarking Embeddings (EWE). Our approach encourages the model to learn features for classifying data that is sampled from the task distribution and data that encodes watermarks. An adversary attempting to remove watermarks that are entangled with legitimate data is also forced to sacrifice performance on legitimate data. Experiments on MNIST, Fashion-MNIST, CIFAR-10, and Speech Commands validate that the defender can claim model ownership with 95\\% confidence with less than 100 queries to the stolen copy, at a modest cost below 0.81 percentage points on average in the defended model's performance.","url_abs":"https://arxiv.org/abs/2002.12200v2","url_pdf":"https://arxiv.org/pdf/2002.12200v2.pdf","source":{"archive":"pwc-archive (Hugging Face), CC BY-SA 4.0","snapshot":"2025-07-28","licence_url":"https://creativecommons.org/licenses/by-sa/4.0/legalcode","row_kind":"abstracts"},"code_links":[{"paper_slug":"entangled-watermarks-as-a-defense-against","repo_url":"https://github.com/cleverhans-lab/entangled-watermark","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"tf","reach":{"status":"ok"}},{"paper_slug":"entangled-watermarks-as-a-defense-against","repo_url":"https://github.com/rorschachchen/entangled-watermark-torch","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok"}},{"paper_slug":"entangled-watermarks-as-a-defense-against","repo_url":"https://github.com/ssg-research/falseclaims","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":null}],"tasks":[{"task_slug":"model-extraction","task_name":"Model extraction"},{"task_slug":"transfer-learning","task_name":"Transfer Learning"},{"task_slug":"model","task_name":"model"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"syntology_url":"https://syntology.ai/paper/2002.12200","atlas_url":"https://app.syntology.ai/?focus=2002.12200","mcp":null,"developers":"https://syntology.ai/developers","held":true,"reason":"arxiv_id_in_atlas","checked_against":{"atlas_ids":549449,"atlas_ids_sha256":"afd72399dafd9906e9062927f70655952385a3d75488558e1f0484e950ab09b7","read_at":"2026-10-05T01:46:21Z"},"agent_calls":[{"tool":"get_citation_path","arguments":{"paper_1":"2002.12200"},"arguments_in":{"paper_2":"another paper's arXiv id or title"},"call":"get_citation_path(paper_1=\"2002.12200\", paper_2=\"…\")"},{"tool":"get_concepts_for_paper","arguments":{"arxiv_id":"2002.12200"},"call":"get_concepts_for_paper(arxiv_id=\"2002.12200\")"}],"by_repo":[{"repo":"cleverhans-lab/entangled-watermark","kind":"official","samples":0,"ran":0,"instrument":0,"unverified":0},{"repo":"rorschachchen/entangled-watermark-torch","kind":"listed","samples":0,"ran":0,"instrument":0,"unverified":0},{"repo":"ssg-research/falseclaims","kind":"listed","samples":0,"ran":0,"instrument":0,"unverified":0,"harvested_for_other_papers":1,"harvested_for":["1802.04633"],"harvested_for_calls":[{"arxiv_id":"1802.04633","tool":"get_harvested_code_for_paper","arguments":{"arxiv_id":"1802.04633"},"call":"get_harvested_code_for_paper(arxiv_id=\"1802.04633\")"}]}],"by_repo_harvested_for_is":"harvested_for: the arXiv ids (as Syntology's graph holds them) of every paper whose samples Syntology's graph links to this repository, in arXiv-id order, complete; the page names the first 3 and says how many more. A link only: it does not say the papers are the same work, that one copied the other, or that the code implements this paper's method; harvested_for_calls gives the get_harvested_code_for_paper call for each arXiv-shaped id among them","by_repo_is":"one row per repository in the archive's code links, Syntology's graph links or the samples; samples 0 means no sample is linked to this paper, a statement about Syntology's coverage, not about the repository: with harvested_for_other_papers present, Syntology harvested the repository for that many other papers, and without it, Syntology harvested nothing from it; placed_by_identical_code counts samples whose link records no repository, placed here because identical code was harvested from this repository for another paper; ran counts executions on a synthesized input and instrument counts failures of Syntology's instrument, not of the code"},"code_links_note":null,"arxiv_metadata":null,"syntology_extracted_results":null,"record_sha256":"68690d8f4962f029ec0d7a2580a13a892b7cb3609a7b756b7f8db477b909c3c1","record_changed_at":"2026-09-28","record_changed_at_basis":"first_hashed"}