{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2023:EOALQK4T4HPH7XJ7E4XFLPBMUM","short_pith_number":"pith:EOALQK4T","schema_version":"1.0","canonical_sha256":"2380b82b93e1de7fdd3f272e55bc2ca307989512d1dc3b6c18b042fba3cfeffd","source":{"kind":"arxiv","id":"2307.06123","version":1},"attestation_state":"computed","paper":{"title":"SoK: Comparing Different Membership Inference Attacks with a Comprehensive Benchmark","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"cs.CR","authors_text":"Chunhui Huang, Ge Zhang, Jianfeng Ma, Jun Niu, Kuo Shen, Moxuan Zeng, Peng Liu, Qingyang Zhao, Suyu An, Weihao Guo, Xiaohong Jiang, Xiaoyan Zhu, Xinghui Yue, Yangming Zhang, Yangzhong Wang, Yulong Shen, Yuqing Zhang, Zhipeng He","submitted_at":"2023-07-12T12:23:47Z","abstract_excerpt":"Membership inference (MI) attacks threaten user privacy through determining if a given data example has been used to train a target model. However, it has been increasingly recognized that the \"comparing different MI attacks\" methodology used in the existing works has serious limitations. Due to these limitations, we found (through the experiments in this work) that some comparison results reported in the literature are quite misleading. In this paper, we seek to develop a comprehensive benchmark for comparing different MI attacks, called MIBench, which consists not only the evaluation metrics"},"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":"2307.06123","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CR","submitted_at":"2023-07-12T12:23:47Z","cross_cats_sorted":["cs.LG"],"title_canon_sha256":"d635d0f43836a9673a713bdc7190dc8ffee9cf83319048be7bf9a61a8d2b090d","abstract_canon_sha256":"256e9ed908ec8d4dc02d274e1c395910ac6daa23e719d522e29e360a0e4059cb"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T06:30:16.971291Z","signature_b64":"zXdLH7tuGloVofLFVWOCmqMAjf81Vb1ho6yO1zTiEdpGZImmN+RPXtdeGknJRHe90ACYZqGf0erYPVdQvgH5CA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"2380b82b93e1de7fdd3f272e55bc2ca307989512d1dc3b6c18b042fba3cfeffd","last_reissued_at":"2026-07-05T06:30:16.970820Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T06:30:16.970820Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"SoK: Comparing Different Membership Inference Attacks with a Comprehensive Benchmark","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"cs.CR","authors_text":"Chunhui Huang, Ge Zhang, Jianfeng Ma, Jun Niu, Kuo Shen, Moxuan Zeng, Peng Liu, Qingyang Zhao, Suyu An, Weihao Guo, Xiaohong Jiang, Xiaoyan Zhu, Xinghui Yue, Yangming Zhang, Yangzhong Wang, Yulong Shen, Yuqing Zhang, Zhipeng He","submitted_at":"2023-07-12T12:23:47Z","abstract_excerpt":"Membership inference (MI) attacks threaten user privacy through determining if a given data example has been used to train a target model. However, it has been increasingly recognized that the \"comparing different MI attacks\" methodology used in the existing works has serious limitations. Due to these limitations, we found (through the experiments in this work) that some comparison results reported in the literature are quite misleading. In this paper, we seek to develop a comprehensive benchmark for comparing different MI attacks, called MIBench, which consists not only the evaluation metrics"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2307.06123","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/2307.06123/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":"2307.06123","created_at":"2026-07-05T06:30:16.970882+00:00"},{"alias_kind":"arxiv_version","alias_value":"2307.06123v1","created_at":"2026-07-05T06:30:16.970882+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2307.06123","created_at":"2026-07-05T06:30:16.970882+00:00"},{"alias_kind":"pith_short_12","alias_value":"EOALQK4T4HPH","created_at":"2026-07-05T06:30:16.970882+00:00"},{"alias_kind":"pith_short_16","alias_value":"EOALQK4T4HPH7XJ7","created_at":"2026-07-05T06:30:16.970882+00:00"},{"alias_kind":"pith_short_8","alias_value":"EOALQK4T","created_at":"2026-07-05T06:30:16.970882+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2506.19360","citing_title":"SoK: Can Synthetic Images Replace Real Data? A Survey of Utility and Privacy of Synthetic Image Generation","ref_index":84,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/EOALQK4T4HPH7XJ7E4XFLPBMUM","json":"https://pith.science/pith/EOALQK4T4HPH7XJ7E4XFLPBMUM.json","graph_json":"https://pith.science/api/pith-number/EOALQK4T4HPH7XJ7E4XFLPBMUM/graph.json","events_json":"https://pith.science/api/pith-number/EOALQK4T4HPH7XJ7E4XFLPBMUM/events.json","paper":"https://pith.science/paper/EOALQK4T"},"agent_actions":{"view_html":"https://pith.science/pith/EOALQK4T4HPH7XJ7E4XFLPBMUM","download_json":"https://pith.science/pith/EOALQK4T4HPH7XJ7E4XFLPBMUM.json","view_paper":"https://pith.science/paper/EOALQK4T","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2307.06123&json=true","fetch_graph":"https://pith.science/api/pith-number/EOALQK4T4HPH7XJ7E4XFLPBMUM/graph.json","fetch_events":"https://pith.science/api/pith-number/EOALQK4T4HPH7XJ7E4XFLPBMUM/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/EOALQK4T4HPH7XJ7E4XFLPBMUM/action/timestamp_anchor","attest_storage":"https://pith.science/pith/EOALQK4T4HPH7XJ7E4XFLPBMUM/action/storage_attestation","attest_author":"https://pith.science/pith/EOALQK4T4HPH7XJ7E4XFLPBMUM/action/author_attestation","sign_citation":"https://pith.science/pith/EOALQK4T4HPH7XJ7E4XFLPBMUM/action/citation_signature","submit_replication":"https://pith.science/pith/EOALQK4T4HPH7XJ7E4XFLPBMUM/action/replication_record"}},"created_at":"2026-07-05T06:30:16.970882+00:00","updated_at":"2026-07-05T06:30:16.970882+00:00"}