{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2022:4FGLWVCD7XNEBEWMM4PL47I7D6","short_pith_number":"pith:4FGLWVCD","schema_version":"1.0","canonical_sha256":"e14cbb5443fdda4092cc671ebe7d1f1f955cb235a96d435daa0e04ca1ed406d1","source":{"kind":"arxiv","id":"2206.03693","version":3},"attestation_state":"computed","paper":{"title":"Autoregressive Perturbations for Data Poisoning","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.CR"],"primary_cat":"cs.LG","authors_text":"David W. Jacobs, Jonas Geiping, Micah Goldblum, Pedro Sandoval-Segura, Tom Goldstein, Vasu Singla","submitted_at":"2022-06-08T06:24:51Z","abstract_excerpt":"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 dat"},"verification_status":{"content_addressed":true,"pith_receipt":true,"author_attested":false,"weak_author_claims":0,"strong_author_claims":0,"externally_anchored":false,"storage_verified":false,"citation_signatures":0,"replication_records":0,"graph_snapshot":true,"references_resolved":false,"formal_links_present":false},"canonical_record":{"source":{"id":"2206.03693","kind":"arxiv","version":3},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2022-06-08T06:24:51Z","cross_cats_sorted":["cs.CR"],"title_canon_sha256":"d34671931d615c3ef148a8fae9e34c61c3ca39c7b092b69dac5efe95078bbc88","abstract_canon_sha256":"679661660ab5d9da42b7bb184ea14ac777cb27c2cc0040eb5367999cc8839efb"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T05:06:32.173074Z","signature_b64":"N8lT9UoRO1EmXJJhxuPkZjuJqytU+2bPlju9yDIJJZTW2IWTgjfVMrMaoW33mxNiBIig7kIZPh7xUepPQdFBCQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"e14cbb5443fdda4092cc671ebe7d1f1f955cb235a96d435daa0e04ca1ed406d1","last_reissued_at":"2026-07-05T05:06:32.172593Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T05:06:32.172593Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Autoregressive Perturbations for Data Poisoning","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.CR"],"primary_cat":"cs.LG","authors_text":"David W. Jacobs, Jonas Geiping, Micah Goldblum, Pedro Sandoval-Segura, Tom Goldstein, Vasu Singla","submitted_at":"2022-06-08T06:24:51Z","abstract_excerpt":"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 dat"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2206.03693","kind":"arxiv","version":3},"verdict":{"id":null,"model_set":{},"created_at":null,"strongest_claim":"","one_line_summary":"","pipeline_version":null,"weakest_assumption":"","pith_extraction_headline":""},"integrity":{"clean":true,"summary":{"advisory":0,"critical":0,"by_detector":{},"informational":0},"endpoint":"/pith/2206.03693/integrity.json","findings":[],"available":true,"detectors_run":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938"},"references":{"count":0,"sample":[],"resolved_work":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57","internal_anchors":0},"formal_canon":{"evidence_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"author_claims":{"count":0,"strong_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"builder_version":"pith-number-builder-2026-05-17-v1"},"aliases":[{"alias_kind":"arxiv","alias_value":"2206.03693","created_at":"2026-07-05T05:06:32.172650+00:00"},{"alias_kind":"arxiv_version","alias_value":"2206.03693v3","created_at":"2026-07-05T05:06:32.172650+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2206.03693","created_at":"2026-07-05T05:06:32.172650+00:00"},{"alias_kind":"pith_short_12","alias_value":"4FGLWVCD7XNE","created_at":"2026-07-05T05:06:32.172650+00:00"},{"alias_kind":"pith_short_16","alias_value":"4FGLWVCD7XNEBEWM","created_at":"2026-07-05T05:06:32.172650+00:00"},{"alias_kind":"pith_short_8","alias_value":"4FGLWVCD","created_at":"2026-07-05T05:06:32.172650+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2406.02883","citing_title":"Nonlinear Transformations Against Unlearnable Datasets","ref_index":33,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/4FGLWVCD7XNEBEWMM4PL47I7D6","json":"https://pith.science/pith/4FGLWVCD7XNEBEWMM4PL47I7D6.json","graph_json":"https://pith.science/api/pith-number/4FGLWVCD7XNEBEWMM4PL47I7D6/graph.json","events_json":"https://pith.science/api/pith-number/4FGLWVCD7XNEBEWMM4PL47I7D6/events.json","paper":"https://pith.science/paper/4FGLWVCD"},"agent_actions":{"view_html":"https://pith.science/pith/4FGLWVCD7XNEBEWMM4PL47I7D6","download_json":"https://pith.science/pith/4FGLWVCD7XNEBEWMM4PL47I7D6.json","view_paper":"https://pith.science/paper/4FGLWVCD","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2206.03693&json=true","fetch_graph":"https://pith.science/api/pith-number/4FGLWVCD7XNEBEWMM4PL47I7D6/graph.json","fetch_events":"https://pith.science/api/pith-number/4FGLWVCD7XNEBEWMM4PL47I7D6/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/4FGLWVCD7XNEBEWMM4PL47I7D6/action/timestamp_anchor","attest_storage":"https://pith.science/pith/4FGLWVCD7XNEBEWMM4PL47I7D6/action/storage_attestation","attest_author":"https://pith.science/pith/4FGLWVCD7XNEBEWMM4PL47I7D6/action/author_attestation","sign_citation":"https://pith.science/pith/4FGLWVCD7XNEBEWMM4PL47I7D6/action/citation_signature","submit_replication":"https://pith.science/pith/4FGLWVCD7XNEBEWMM4PL47I7D6/action/replication_record"}},"created_at":"2026-07-05T05:06:32.172650+00:00","updated_at":"2026-07-05T05:06:32.172650+00:00"}