{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2026:KDKO24KZQDUQOV3CCS7IZSLNU2","short_pith_number":"pith:KDKO24KZ","schema_version":"1.0","canonical_sha256":"50d4ed715980e907576214be8cc96da6b1c6a3e9f40729a41d985cf946e07c5a","source":{"kind":"arxiv","id":"2607.04339","version":1},"attestation_state":"computed","paper":{"title":"One Framework for All: Cross-Modal Membership Inference for Generative Models","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","headline":"","cross_cats":["cs.AI","cs.CR"],"primary_cat":"cs.LG","authors_text":"Bo Liu, Dayong Ye, Hengzhu Liu, Junhao Liu, Kun Gao, Shuai Zhou, Tainqing Zhu, Wanlei Zhou, Yichuan Chen","submitted_at":"2026-07-05T14:45:29Z","abstract_excerpt":"Large generative models across text-to-text, text-to-image, and image-to-text modalities have been shown to pose significant privacy risks. One fundamental threat is membership inference attacks (MIA), which aim to determine whether a given data point was used in a model's training set. Although prior work has investigated MIAs against these three classes of generative models, existing approaches treat them in isolation and are not cross-applicable, thereby limiting their real-world utility. To address this limitation, we present the first comprehensive study of a unified membership inference "},"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":"2607.04339","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.LG","submitted_at":"2026-07-05T14:45:29Z","cross_cats_sorted":["cs.AI","cs.CR"],"title_canon_sha256":"3039a5596eb5d398b7f48c1052b0e13101f25b077ef81536d58fbee65aa4ee4c","abstract_canon_sha256":"9baf5c916999b709530243927ca67cb070a5dfc3198373bb3a4fb8a457dc5b78"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-07T02:19:09.821510Z","signature_b64":"kzRfMzL6cjsDRRpvBKOZx3zTCul6QcVrM9GejzjMAFgzLDRnTf4mWX9c+7lN/h683kXKV8YfEk7hXjs2ikovDw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"50d4ed715980e907576214be8cc96da6b1c6a3e9f40729a41d985cf946e07c5a","last_reissued_at":"2026-07-07T02:19:09.820306Z","signature_status":"signed_v1","first_computed_at":"2026-07-07T02:19:09.820306Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"One Framework for All: Cross-Modal Membership Inference for Generative Models","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","headline":"","cross_cats":["cs.AI","cs.CR"],"primary_cat":"cs.LG","authors_text":"Bo Liu, Dayong Ye, Hengzhu Liu, Junhao Liu, Kun Gao, Shuai Zhou, Tainqing Zhu, Wanlei Zhou, Yichuan Chen","submitted_at":"2026-07-05T14:45:29Z","abstract_excerpt":"Large generative models across text-to-text, text-to-image, and image-to-text modalities have been shown to pose significant privacy risks. One fundamental threat is membership inference attacks (MIA), which aim to determine whether a given data point was used in a model's training set. Although prior work has investigated MIAs against these three classes of generative models, existing approaches treat them in isolation and are not cross-applicable, thereby limiting their real-world utility. To address this limitation, we present the first comprehensive study of a unified membership inference "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2607.04339","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/2607.04339/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":"2607.04339","created_at":"2026-07-07T02:19:09.820450+00:00"},{"alias_kind":"arxiv_version","alias_value":"2607.04339v1","created_at":"2026-07-07T02:19:09.820450+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2607.04339","created_at":"2026-07-07T02:19:09.820450+00:00"},{"alias_kind":"pith_short_12","alias_value":"KDKO24KZQDUQ","created_at":"2026-07-07T02:19:09.820450+00:00"},{"alias_kind":"pith_short_16","alias_value":"KDKO24KZQDUQOV3C","created_at":"2026-07-07T02:19:09.820450+00:00"},{"alias_kind":"pith_short_8","alias_value":"KDKO24KZ","created_at":"2026-07-07T02:19:09.820450+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/KDKO24KZQDUQOV3CCS7IZSLNU2","json":"https://pith.science/pith/KDKO24KZQDUQOV3CCS7IZSLNU2.json","graph_json":"https://pith.science/api/pith-number/KDKO24KZQDUQOV3CCS7IZSLNU2/graph.json","events_json":"https://pith.science/api/pith-number/KDKO24KZQDUQOV3CCS7IZSLNU2/events.json","paper":"https://pith.science/paper/KDKO24KZ"},"agent_actions":{"view_html":"https://pith.science/pith/KDKO24KZQDUQOV3CCS7IZSLNU2","download_json":"https://pith.science/pith/KDKO24KZQDUQOV3CCS7IZSLNU2.json","view_paper":"https://pith.science/paper/KDKO24KZ","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2607.04339&json=true","fetch_graph":"https://pith.science/api/pith-number/KDKO24KZQDUQOV3CCS7IZSLNU2/graph.json","fetch_events":"https://pith.science/api/pith-number/KDKO24KZQDUQOV3CCS7IZSLNU2/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/KDKO24KZQDUQOV3CCS7IZSLNU2/action/timestamp_anchor","attest_storage":"https://pith.science/pith/KDKO24KZQDUQOV3CCS7IZSLNU2/action/storage_attestation","attest_author":"https://pith.science/pith/KDKO24KZQDUQOV3CCS7IZSLNU2/action/author_attestation","sign_citation":"https://pith.science/pith/KDKO24KZQDUQOV3CCS7IZSLNU2/action/citation_signature","submit_replication":"https://pith.science/pith/KDKO24KZQDUQOV3CCS7IZSLNU2/action/replication_record"}},"created_at":"2026-07-07T02:19:09.820450+00:00","updated_at":"2026-07-07T02:19:09.820450+00:00"}