{"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/stronger-data-poisoning-attacks-break-data","title":"Stronger Data Poisoning Attacks Break Data Sanitization Defenses","arxiv_id":"1811.00741","date":"2018-11-02","proceeding":null,"authors":["Pang Wei Koh","Jacob Steinhardt","Percy Liang"],"abstract":"Machine learning models trained on data from the outside world can be corrupted by data poisoning attacks that inject malicious points into the models' training sets. A common defense against these attacks is data sanitization: first filter out anomalous training points before training the model. In this paper, we develop three attacks that can bypass a broad range of common data sanitization defenses, including anomaly detectors based on nearest neighbors, training loss, and singular-value decomposition. By adding just 3% poisoned data, our attacks successfully increase test error on the Enron spam detection dataset from 3% to 24% and on the IMDB sentiment classification dataset from 12% to 29%. In contrast, existing attacks which do not explicitly account for these data sanitization defenses are defeated by them. Our attacks are based on two ideas: (i) we coordinate our attacks to place poisoned points near one another, and (ii) we formulate each attack as a constrained optimization problem, with constraints designed to ensure that the poisoned points evade detection. As this optimization involves solving an expensive bilevel problem, our three attacks correspond to different ways of approximating this problem, based on influence functions; minimax duality; and the Karush-Kuhn-Tucker (KKT) conditions. Our results underscore the need to develop more robust defenses against data poisoning attacks.","url_abs":"https://arxiv.org/abs/1811.00741v2","url_pdf":"https://arxiv.org/pdf/1811.00741v2.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":"stronger-data-poisoning-attacks-break-data","repo_url":"https://github.com/kohpangwei/data-poisoning-journal-release","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"tf","reach":{"status":"ok"}},{"paper_slug":"stronger-data-poisoning-attacks-break-data","repo_url":"https://github.com/suyeecav/model-targeted-poisoning","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok"}}],"tasks":[{"task_slug":"data-poisoning","task_name":"Data Poisoning"},{"task_slug":"sentiment-analysis","task_name":"Sentiment Analysis"},{"task_slug":"sentiment-classification","task_name":"Sentiment Classification"},{"task_slug":"spam-detection","task_name":"Spam detection"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"syntology_url":"https://syntology.ai/paper/1811.00741","atlas_url":"https://app.syntology.ai/?focus=1811.00741","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":"1811.00741"},"arguments_in":{"paper_2":"another paper's arXiv id or title"},"call":"get_citation_path(paper_1=\"1811.00741\", paper_2=\"…\")"},{"tool":"get_concepts_for_paper","arguments":{"arxiv_id":"1811.00741"},"call":"get_concepts_for_paper(arxiv_id=\"1811.00741\")"}],"by_repo":[{"repo":"kohpangwei/data-poisoning-journal-release","kind":"official","samples":0,"ran":0,"instrument":0,"unverified":0},{"repo":"suyeecav/model-targeted-poisoning","kind":"listed","samples":0,"ran":0,"instrument":0,"unverified":0}],"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":"b2922cc8536656e2a0fe26da3874476a85aef297c0a7871cb1171a8e7fcbe9df","record_changed_at":"2026-09-28","record_changed_at_basis":"first_hashed"}