{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2022:L5HIA2TT7ESYGSCQV3YHOJBTJY","short_pith_number":"pith:L5HIA2TT","schema_version":"1.0","canonical_sha256":"5f4e806a73f925834850aef07724334e3ea0e906ffbc7cd00e72b01b8f3f4813","source":{"kind":"arxiv","id":"2204.09092","version":2},"attestation_state":"computed","paper":{"title":"Indiscriminate Data Poisoning Attacks on Neural Networks","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.CR"],"primary_cat":"cs.LG","authors_text":"Gautam Kamath, Yaoliang Yu, Yiwei Lu","submitted_at":"2022-04-19T18:57:26Z","abstract_excerpt":"Data poisoning attacks, in which a malicious adversary aims to influence a model by injecting \"poisoned\" data into the training process, have attracted significant recent attention. In this work, we take a closer look at existing poisoning attacks and connect them with old and new algorithms for solving sequential Stackelberg games. By choosing an appropriate loss function for the attacker and optimizing with algorithms that exploit second-order information, we design poisoning attacks that are effective on neural networks. We present efficient implementations that exploit modern auto-differen"},"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":"2204.09092","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2022-04-19T18:57:26Z","cross_cats_sorted":["cs.CR"],"title_canon_sha256":"fc0ec5723d3983514b130ccdba63d0234658bc6b20753fe66070ac25e3e26f35","abstract_canon_sha256":"46883d28052437e1e2830305b48d4adc48cae7ee21a7ec4f1316a151687bf0c1"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T07:45:24.879111Z","signature_b64":"aN0ccQKOD/IU/daZGz3O1ywi5DhLwwh+GO65HWM2IkdnswnB0Sq83zv+XSGQ5OkJ+Fod99pe1YOF/Prnr5qXDA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"5f4e806a73f925834850aef07724334e3ea0e906ffbc7cd00e72b01b8f3f4813","last_reissued_at":"2026-07-05T07:45:24.878738Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T07:45:24.878738Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Indiscriminate Data Poisoning Attacks on Neural Networks","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.CR"],"primary_cat":"cs.LG","authors_text":"Gautam Kamath, Yaoliang Yu, Yiwei Lu","submitted_at":"2022-04-19T18:57:26Z","abstract_excerpt":"Data poisoning attacks, in which a malicious adversary aims to influence a model by injecting \"poisoned\" data into the training process, have attracted significant recent attention. In this work, we take a closer look at existing poisoning attacks and connect them with old and new algorithms for solving sequential Stackelberg games. By choosing an appropriate loss function for the attacker and optimizing with algorithms that exploit second-order information, we design poisoning attacks that are effective on neural networks. We present efficient implementations that exploit modern auto-differen"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2204.09092","kind":"arxiv","version":2},"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/2204.09092/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":"2204.09092","created_at":"2026-07-05T07:45:24.878795+00:00"},{"alias_kind":"arxiv_version","alias_value":"2204.09092v2","created_at":"2026-07-05T07:45:24.878795+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2204.09092","created_at":"2026-07-05T07:45:24.878795+00:00"},{"alias_kind":"pith_short_12","alias_value":"L5HIA2TT7ESY","created_at":"2026-07-05T07:45:24.878795+00:00"},{"alias_kind":"pith_short_16","alias_value":"L5HIA2TT7ESYGSCQ","created_at":"2026-07-05T07:45:24.878795+00:00"},{"alias_kind":"pith_short_8","alias_value":"L5HIA2TT","created_at":"2026-07-05T07:45:24.878795+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2506.01230","citing_title":"Stress-Testing ML Pipelines with Adversarial Data Corruption","ref_index":32,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/L5HIA2TT7ESYGSCQV3YHOJBTJY","json":"https://pith.science/pith/L5HIA2TT7ESYGSCQV3YHOJBTJY.json","graph_json":"https://pith.science/api/pith-number/L5HIA2TT7ESYGSCQV3YHOJBTJY/graph.json","events_json":"https://pith.science/api/pith-number/L5HIA2TT7ESYGSCQV3YHOJBTJY/events.json","paper":"https://pith.science/paper/L5HIA2TT"},"agent_actions":{"view_html":"https://pith.science/pith/L5HIA2TT7ESYGSCQV3YHOJBTJY","download_json":"https://pith.science/pith/L5HIA2TT7ESYGSCQV3YHOJBTJY.json","view_paper":"https://pith.science/paper/L5HIA2TT","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2204.09092&json=true","fetch_graph":"https://pith.science/api/pith-number/L5HIA2TT7ESYGSCQV3YHOJBTJY/graph.json","fetch_events":"https://pith.science/api/pith-number/L5HIA2TT7ESYGSCQV3YHOJBTJY/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/L5HIA2TT7ESYGSCQV3YHOJBTJY/action/timestamp_anchor","attest_storage":"https://pith.science/pith/L5HIA2TT7ESYGSCQV3YHOJBTJY/action/storage_attestation","attest_author":"https://pith.science/pith/L5HIA2TT7ESYGSCQV3YHOJBTJY/action/author_attestation","sign_citation":"https://pith.science/pith/L5HIA2TT7ESYGSCQV3YHOJBTJY/action/citation_signature","submit_replication":"https://pith.science/pith/L5HIA2TT7ESYGSCQV3YHOJBTJY/action/replication_record"}},"created_at":"2026-07-05T07:45:24.878795+00:00","updated_at":"2026-07-05T07:45:24.878795+00:00"}