{"about":{"site":"https://codewithpapers.app","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.","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"},"url":"/paper/exploring-the-limits-of-indiscriminate-data","title":"Exploring the Limits of Model-Targeted Indiscriminate Data Poisoning Attacks","arxiv_id":"2303.03592","date":"2023-03-07","proceeding":null,"authors":["Yiwei Lu","Gautam Kamath","YaoLiang Yu"],"abstract":"Indiscriminate data poisoning attacks aim to decrease a model's test accuracy by injecting a small amount of corrupted training data. Despite significant interest, existing attacks remain relatively ineffective against modern machine learning (ML) architectures. In this work, we introduce the notion of model poisoning reachability as a technical tool to explore the intrinsic limits of data poisoning attacks towards target parameters (i.e., model-targeted attacks). We derive an easily computable threshold to establish and quantify a surprising phase transition phenomenon among popular ML models: data poisoning attacks can achieve certain target parameters only when the poisoning ratio exceeds our threshold. Building on existing parameter corruption attacks and refining the Gradient Canceling attack, we perform extensive experiments to confirm our theoretical findings, test the predictability of our transition threshold, and significantly improve existing indiscriminate data poisoning baselines over a range of datasets and models. Our work highlights the critical role played by the poisoning ratio, and sheds new insights on existing empirical results, attacks and mitigation strategies in data poisoning.","url_abs":"https://arxiv.org/abs/2303.03592v3","url_pdf":"https://arxiv.org/pdf/2303.03592v3.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":"exploring-the-limits-of-indiscriminate-data","repo_url":"https://github.com/watml/plim","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":0,"framework":"pytorch","reach":null}],"tasks":[{"task_slug":"data-poisoning","task_name":"Data Poisoning"},{"task_slug":"model-poisoning","task_name":"Model Poisoning"}],"methods":[{"method_slug":"test","method_name":"Test"}],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"syntology_url":null,"atlas_url":"https://app.syntology.ai/?focus=2303.03592","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2303.03592"}},"developers":"https://syntology.ai/developers","read_at":"2026-09-24T18:15:14+00:00","read_at_is":"when the build read Syntology's graph, not when any sample ran","claim":"Per-sample execution status on synthesized fixtures; not a correctness claim about the paper. Samples come from repositories linked to the paper, official or community; repo_kind says which.","repos":[{"provenance":"deterministic:regex_extraction","url":"https://github.com/watml/plim","reach":null}],"summary":{"ran_honours":2,"ran":1},"by_repo_kind":{"official":{"samples":3,"ran":3,"repositories":1}},"repo_kind_vocabulary":{"official":"The archive marks this repository official for the paper","named_in_paper":"The archive records that the paper mentions this repository; it is not marked official","listed":"In the archive's code links for this paper, not marked official and not recorded as mentioned in the paper","found_in_text":"Syntology found this repository in the paper's own text; whether it is the authors' implementation is not asserted","community":"Not in the archive's code links for this paper; a community repository Syntology harvested"},"n_pointer_only_for_licence":3,"samples":[{"code_sha256_prefix":"5786f2f8ac2d4de4","entry":"autograd","repo":"watml/plim","repo_kind":"official","path":"GC/mnist_cnn-0.03.py","file_url":"https://github.com/watml/plim/blob/HEAD/GC/mnist_cnn-0.03.py","link_basis":"first_harvest_node","language":"python","status":"ran_honours","verification_level":2,"contract_check":"HONOURS","metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"5786f2f8ac2d4de4"}},{"code_sha256_prefix":"bbac4a1a065fc6b1","entry":"GradAttacker","repo":"watml/plim","repo_kind":"official","path":"GradPC/attacker.py","file_url":"https://github.com/watml/plim/blob/HEAD/GradPC/attacker.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"bbac4a1a065fc6b1"}},{"code_sha256_prefix":"6d1ef22707974df2","entry":"adjust_learning_rate","repo":"watml/plim","repo_kind":"official","path":"GC/mnist_cnn-0.03.py","file_url":"https://github.com/watml/plim/blob/HEAD/GC/mnist_cnn-0.03.py","link_basis":"first_harvest_node","language":"python","status":"ran_honours","verification_level":1,"contract_check":"HONOURS","metamorphic_tier":"well_formed","behaviour_fingerprint":true,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"6d1ef22707974df2"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}