{"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/autoregressive-perturbations-for-data","title":"Autoregressive Perturbations for Data Poisoning","arxiv_id":"2206.03693","date":"2022-06-08","proceeding":null,"authors":["Pedro Sandoval-Segura","Vasu Singla","Jonas Geiping","Micah Goldblum","Tom Goldstein","David W. Jacobs"],"abstract":"The prevalence of data scraping from social media as a means to obtain datasets has led to growing concerns regarding unauthorized use of data. Data poisoning attacks have been proposed as a bulwark against scraping, as they make data \"unlearnable\" by adding small, imperceptible perturbations. Unfortunately, existing methods require knowledge of both the target architecture and the complete dataset so that a surrogate network can be trained, the parameters of which are used to generate the attack. In this work, we introduce autoregressive (AR) poisoning, a method that can generate poisoned data without access to the broader dataset. The proposed AR perturbations are generic, can be applied across different datasets, and can poison different architectures. Compared to existing unlearnable methods, our AR poisons are more resistant against common defenses such as adversarial training and strong data augmentations. Our analysis further provides insight into what makes an effective data poison.","url_abs":"https://arxiv.org/abs/2206.03693v3","url_pdf":"https://arxiv.org/pdf/2206.03693v3.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":"autoregressive-perturbations-for-data","repo_url":"https://github.com/psandovalsegura/autoregressive-poisoning","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"pytorch","reach":null},{"paper_slug":"autoregressive-perturbations-for-data","repo_url":"https://github.com/psandovalsegura/learn-from-unlearnable","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":null}],"tasks":[{"task_slug":"data-poisoning","task_name":"Data Poisoning"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=2206.03693","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2206.03693"}},"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":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/psandovalsegura/learn-from-unlearnable","reach":null},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/psandovalsegura/autoregressive-poisoning","reach":null}],"summary":{"ran":1,"ran_fixture":1,"ran_draft_wrong":1,"unverified":2},"by_repo_kind":{"official":{"samples":3,"ran":2,"repositories":1},"listed":{"samples":2,"ran":1,"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":2,"samples":[{"code_sha256_prefix":"060b77a13d61aa6d","entry":"ARProcessPerturb3Channel","repo":"psandovalsegura/autoregressive-poisoning","repo_kind":"official","path":"autoregressive.py","file_url":"https://github.com/psandovalsegura/autoregressive-poisoning/blob/HEAD/autoregressive.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":"deterministic","behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"060b77a13d61aa6d"}},{"code_sha256_prefix":"164f4838834c6092","entry":"eval_on_loader","repo":"psandovalsegura/learn-from-unlearnable","repo_kind":"listed","path":"dfr_step_1.py","file_url":"https://github.com/psandovalsegura/learn-from-unlearnable/blob/HEAD/dfr_step_1.py","link_basis":"first_harvest_node","language":"python","status":"ran_fixture","verification_level":1,"contract_check":"RAISES","metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"164f4838834c6092"}},{"code_sha256_prefix":"48b84fc945bc8e86","entry":"perturb_with_ar_process","repo":"psandovalsegura/autoregressive-poisoning","repo_kind":"official","path":"create_ar_poisons_3channel.py","file_url":"https://github.com/psandovalsegura/autoregressive-poisoning/blob/HEAD/create_ar_poisons_3channel.py","link_basis":"first_harvest_node","language":"python","status":"ran_draft_wrong","verification_level":1,"contract_check":"MISDECLARED","metamorphic_tier":"invariant","behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"48b84fc945bc8e86"}},{"code_sha256_prefix":"ee60eb57e628b222","entry":"export_poison","repo":"psandovalsegura/autoregressive-poisoning","repo_kind":"official","path":"create_ar_poisons_3channel.py","file_url":"https://github.com/psandovalsegura/autoregressive-poisoning/blob/HEAD/create_ar_poisons_3channel.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"ee60eb57e628b222"}},{"code_sha256_prefix":"4fe69afc04e54986","entry":"train_model","repo":"psandovalsegura/learn-from-unlearnable","repo_kind":"listed","path":"dfr_step_1.py","file_url":"https://github.com/psandovalsegura/learn-from-unlearnable/blob/HEAD/dfr_step_1.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"4fe69afc04e54986"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}