{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2023:XK4CQTHACU735MG3WYHLCUIOSN","short_pith_number":"pith:XK4CQTHA","schema_version":"1.0","canonical_sha256":"bab8284ce0153fbeb0dbb60eb1510e9374b7064f272a6ce2f6b67a3167063eae","source":{"kind":"arxiv","id":"2306.03726","version":1},"attestation_state":"computed","paper":{"title":"Exploring Model Dynamics for Accumulative Poisoning Discovery","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.CR"],"primary_cat":"cs.LG","authors_text":"Bo Han, Chao Du, Jiangchao Yao, Jianing Zhu, Liang Wang, Li He, Shuo Yuan, Tongliang Liu, Xiawei Guo","submitted_at":"2023-06-06T14:45:24Z","abstract_excerpt":"Adversarial poisoning attacks pose huge threats to various machine learning applications. Especially, the recent accumulative poisoning attacks show that it is possible to achieve irreparable harm on models via a sequence of imperceptible attacks followed by a trigger batch. Due to the limited data-level discrepancy in real-time data streaming, current defensive methods are indiscriminate in handling the poison and clean samples. In this paper, we dive into the perspective of model dynamics and propose a novel information measure, namely, Memorization Discrepancy, to explore the defense via th"},"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":"2306.03726","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2023-06-06T14:45:24Z","cross_cats_sorted":["cs.CR"],"title_canon_sha256":"7ba7f995f550a3b545f798209784de5ec67c9aecb0cb6a267bd9054a3c73956c","abstract_canon_sha256":"020feaa1ff902c428de76336367815f33ec6988c637900ecf4029754e1d75624"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T06:18:01.354218Z","signature_b64":"lI/Jr1MCbVBkkOHPf6v/R0+T9d9J3CjEqboeqdYJi+JQNcfeIJ970ZyKPckr1iEcD/sO6TFr7W4LT2r1ByY9BQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"bab8284ce0153fbeb0dbb60eb1510e9374b7064f272a6ce2f6b67a3167063eae","last_reissued_at":"2026-07-05T06:18:01.353876Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T06:18:01.353876Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Exploring Model Dynamics for Accumulative Poisoning Discovery","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.CR"],"primary_cat":"cs.LG","authors_text":"Bo Han, Chao Du, Jiangchao Yao, Jianing Zhu, Liang Wang, Li He, Shuo Yuan, Tongliang Liu, Xiawei Guo","submitted_at":"2023-06-06T14:45:24Z","abstract_excerpt":"Adversarial poisoning attacks pose huge threats to various machine learning applications. Especially, the recent accumulative poisoning attacks show that it is possible to achieve irreparable harm on models via a sequence of imperceptible attacks followed by a trigger batch. Due to the limited data-level discrepancy in real-time data streaming, current defensive methods are indiscriminate in handling the poison and clean samples. In this paper, we dive into the perspective of model dynamics and propose a novel information measure, namely, Memorization Discrepancy, to explore the defense via th"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2306.03726","kind":"arxiv","version":1},"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/2306.03726/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":"2306.03726","created_at":"2026-07-05T06:18:01.353932+00:00"},{"alias_kind":"arxiv_version","alias_value":"2306.03726v1","created_at":"2026-07-05T06:18:01.353932+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2306.03726","created_at":"2026-07-05T06:18:01.353932+00:00"},{"alias_kind":"pith_short_12","alias_value":"XK4CQTHACU73","created_at":"2026-07-05T06:18:01.353932+00:00"},{"alias_kind":"pith_short_16","alias_value":"XK4CQTHACU735MG3","created_at":"2026-07-05T06:18:01.353932+00:00"},{"alias_kind":"pith_short_8","alias_value":"XK4CQTHA","created_at":"2026-07-05T06:18:01.353932+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":0,"internal_anchor_count":0,"sample":[]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/XK4CQTHACU735MG3WYHLCUIOSN","json":"https://pith.science/pith/XK4CQTHACU735MG3WYHLCUIOSN.json","graph_json":"https://pith.science/api/pith-number/XK4CQTHACU735MG3WYHLCUIOSN/graph.json","events_json":"https://pith.science/api/pith-number/XK4CQTHACU735MG3WYHLCUIOSN/events.json","paper":"https://pith.science/paper/XK4CQTHA"},"agent_actions":{"view_html":"https://pith.science/pith/XK4CQTHACU735MG3WYHLCUIOSN","download_json":"https://pith.science/pith/XK4CQTHACU735MG3WYHLCUIOSN.json","view_paper":"https://pith.science/paper/XK4CQTHA","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2306.03726&json=true","fetch_graph":"https://pith.science/api/pith-number/XK4CQTHACU735MG3WYHLCUIOSN/graph.json","fetch_events":"https://pith.science/api/pith-number/XK4CQTHACU735MG3WYHLCUIOSN/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/XK4CQTHACU735MG3WYHLCUIOSN/action/timestamp_anchor","attest_storage":"https://pith.science/pith/XK4CQTHACU735MG3WYHLCUIOSN/action/storage_attestation","attest_author":"https://pith.science/pith/XK4CQTHACU735MG3WYHLCUIOSN/action/author_attestation","sign_citation":"https://pith.science/pith/XK4CQTHACU735MG3WYHLCUIOSN/action/citation_signature","submit_replication":"https://pith.science/pith/XK4CQTHACU735MG3WYHLCUIOSN/action/replication_record"}},"created_at":"2026-07-05T06:18:01.353932+00:00","updated_at":"2026-07-05T06:18:01.353932+00:00"}