{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:66UENQJR2IG3SYCAEWJ656EKSP","short_pith_number":"pith:66UENQJR","schema_version":"1.0","canonical_sha256":"f7a846c131d20db960402593eef88a93cd2d08087a90862d340e02e2dec76066","source":{"kind":"arxiv","id":"2407.15098","version":1},"attestation_state":"computed","paper":{"title":"SeqMIA: Sequential-Metric Based Membership Inference Attack","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"cs.CR","authors_text":"Chengrui Hu, Dengguo Feng, Hao Li, Min Zhang, Siyuan Wu, Yang Zhang, Yutong Ye, Zheng Li","submitted_at":"2024-07-21T09:11:08Z","abstract_excerpt":"Most existing membership inference attacks (MIAs) utilize metrics (e.g., loss) calculated on the model's final state, while recent advanced attacks leverage metrics computed at various stages, including both intermediate and final stages, throughout the model training. Nevertheless, these attacks often process multiple intermediate states of the metric independently, ignoring their time-dependent patterns. Consequently, they struggle to effectively distinguish between members and non-members who exhibit similar metric values, particularly resulting in a high false-positive rate.\n  In this stud"},"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":"2407.15098","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CR","submitted_at":"2024-07-21T09:11:08Z","cross_cats_sorted":["cs.LG"],"title_canon_sha256":"dd295ddfa1a130aa32d9f6b63f97931dfcf733e360b87b2f5c9b8aa966e97ff0","abstract_canon_sha256":"e4bd59e51347bad1dd48a485005f145ab0de5a2488b022ddffe7daef86b926db"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T08:46:38.852649Z","signature_b64":"buyRN07ub/PzqNKD909qZsppfJbuPuNPb04E12Ek8n5sVZXLjBqq5mPlmQoR21b9/qDBlsItQkZWMNhd/f69BQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"f7a846c131d20db960402593eef88a93cd2d08087a90862d340e02e2dec76066","last_reissued_at":"2026-07-05T08:46:38.852198Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T08:46:38.852198Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"SeqMIA: Sequential-Metric Based Membership Inference Attack","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"cs.CR","authors_text":"Chengrui Hu, Dengguo Feng, Hao Li, Min Zhang, Siyuan Wu, Yang Zhang, Yutong Ye, Zheng Li","submitted_at":"2024-07-21T09:11:08Z","abstract_excerpt":"Most existing membership inference attacks (MIAs) utilize metrics (e.g., loss) calculated on the model's final state, while recent advanced attacks leverage metrics computed at various stages, including both intermediate and final stages, throughout the model training. Nevertheless, these attacks often process multiple intermediate states of the metric independently, ignoring their time-dependent patterns. Consequently, they struggle to effectively distinguish between members and non-members who exhibit similar metric values, particularly resulting in a high false-positive rate.\n  In this stud"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2407.15098","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/2407.15098/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":"2407.15098","created_at":"2026-07-05T08:46:38.852253+00:00"},{"alias_kind":"arxiv_version","alias_value":"2407.15098v1","created_at":"2026-07-05T08:46:38.852253+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2407.15098","created_at":"2026-07-05T08:46:38.852253+00:00"},{"alias_kind":"pith_short_12","alias_value":"66UENQJR2IG3","created_at":"2026-07-05T08:46:38.852253+00:00"},{"alias_kind":"pith_short_16","alias_value":"66UENQJR2IG3SYCA","created_at":"2026-07-05T08:46:38.852253+00:00"},{"alias_kind":"pith_short_8","alias_value":"66UENQJR","created_at":"2026-07-05T08:46:38.852253+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2506.07888","citing_title":"SoK: Data Reconstruction Attacks Against Machine Learning Models: Definition, Metrics, and Benchmark","ref_index":33,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/66UENQJR2IG3SYCAEWJ656EKSP","json":"https://pith.science/pith/66UENQJR2IG3SYCAEWJ656EKSP.json","graph_json":"https://pith.science/api/pith-number/66UENQJR2IG3SYCAEWJ656EKSP/graph.json","events_json":"https://pith.science/api/pith-number/66UENQJR2IG3SYCAEWJ656EKSP/events.json","paper":"https://pith.science/paper/66UENQJR"},"agent_actions":{"view_html":"https://pith.science/pith/66UENQJR2IG3SYCAEWJ656EKSP","download_json":"https://pith.science/pith/66UENQJR2IG3SYCAEWJ656EKSP.json","view_paper":"https://pith.science/paper/66UENQJR","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2407.15098&json=true","fetch_graph":"https://pith.science/api/pith-number/66UENQJR2IG3SYCAEWJ656EKSP/graph.json","fetch_events":"https://pith.science/api/pith-number/66UENQJR2IG3SYCAEWJ656EKSP/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/66UENQJR2IG3SYCAEWJ656EKSP/action/timestamp_anchor","attest_storage":"https://pith.science/pith/66UENQJR2IG3SYCAEWJ656EKSP/action/storage_attestation","attest_author":"https://pith.science/pith/66UENQJR2IG3SYCAEWJ656EKSP/action/author_attestation","sign_citation":"https://pith.science/pith/66UENQJR2IG3SYCAEWJ656EKSP/action/citation_signature","submit_replication":"https://pith.science/pith/66UENQJR2IG3SYCAEWJ656EKSP/action/replication_record"}},"created_at":"2026-07-05T08:46:38.852253+00:00","updated_at":"2026-07-05T08:46:38.852253+00:00"}