{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:6D2NQDXIHEIZNHDTRRY2GKMRVY","short_pith_number":"pith:6D2NQDXI","schema_version":"1.0","canonical_sha256":"f0f4d80ee83911969c738c71a32991ae3a2fe544f1fcd5f0affbcfd05315ed5d","source":{"kind":"arxiv","id":"2506.14919","version":1},"attestation_state":"computed","paper":{"title":"Frequency-Calibrated Membership Inference Attacks on Medical Image Diffusion Models","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"cs.CV","authors_text":"Junichiro Iwasawa, Keita Oda, Xinkai Zhao, Yuta Tokuoka","submitted_at":"2025-06-17T18:59:43Z","abstract_excerpt":"The increasing use of diffusion models for image generation, especially in sensitive areas like medical imaging, has raised significant privacy concerns. Membership Inference Attack (MIA) has emerged as a potential approach to determine if a specific image was used to train a diffusion model, thus quantifying privacy risks. Existing MIA methods often rely on diffusion reconstruction errors, where member images are expected to have lower reconstruction errors than non-member images. However, applying these methods directly to medical images faces challenges. Reconstruction error is influenced b"},"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":"2506.14919","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2025-06-17T18:59:43Z","cross_cats_sorted":["cs.LG"],"title_canon_sha256":"8897c5daa2a1df538c7b433cffae203eb72c1fe12956352d16ac4c632c234b13","abstract_canon_sha256":"5da33974685813cb5851df4002dd93dc87b3b07e3b653deb0a2aa57df3024288"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:23:34.086211Z","signature_b64":"IjS37TK1uyDINbXaj1wNvTt6H+c63m7yJCwTWj48a6UvpaIuiQ4n9b1J4p1IvUtYxQlfYBIrNtqQpTkbwNhMCQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"f0f4d80ee83911969c738c71a32991ae3a2fe544f1fcd5f0affbcfd05315ed5d","last_reissued_at":"2026-07-05T11:23:34.085721Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:23:34.085721Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Frequency-Calibrated Membership Inference Attacks on Medical Image Diffusion Models","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"cs.CV","authors_text":"Junichiro Iwasawa, Keita Oda, Xinkai Zhao, Yuta Tokuoka","submitted_at":"2025-06-17T18:59:43Z","abstract_excerpt":"The increasing use of diffusion models for image generation, especially in sensitive areas like medical imaging, has raised significant privacy concerns. Membership Inference Attack (MIA) has emerged as a potential approach to determine if a specific image was used to train a diffusion model, thus quantifying privacy risks. Existing MIA methods often rely on diffusion reconstruction errors, where member images are expected to have lower reconstruction errors than non-member images. However, applying these methods directly to medical images faces challenges. Reconstruction error is influenced b"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2506.14919","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/2506.14919/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":"2506.14919","created_at":"2026-07-05T11:23:34.085780+00:00"},{"alias_kind":"arxiv_version","alias_value":"2506.14919v1","created_at":"2026-07-05T11:23:34.085780+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2506.14919","created_at":"2026-07-05T11:23:34.085780+00:00"},{"alias_kind":"pith_short_12","alias_value":"6D2NQDXIHEIZ","created_at":"2026-07-05T11:23:34.085780+00:00"},{"alias_kind":"pith_short_16","alias_value":"6D2NQDXIHEIZNHDT","created_at":"2026-07-05T11:23:34.085780+00:00"},{"alias_kind":"pith_short_8","alias_value":"6D2NQDXI","created_at":"2026-07-05T11:23:34.085780+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/6D2NQDXIHEIZNHDTRRY2GKMRVY","json":"https://pith.science/pith/6D2NQDXIHEIZNHDTRRY2GKMRVY.json","graph_json":"https://pith.science/api/pith-number/6D2NQDXIHEIZNHDTRRY2GKMRVY/graph.json","events_json":"https://pith.science/api/pith-number/6D2NQDXIHEIZNHDTRRY2GKMRVY/events.json","paper":"https://pith.science/paper/6D2NQDXI"},"agent_actions":{"view_html":"https://pith.science/pith/6D2NQDXIHEIZNHDTRRY2GKMRVY","download_json":"https://pith.science/pith/6D2NQDXIHEIZNHDTRRY2GKMRVY.json","view_paper":"https://pith.science/paper/6D2NQDXI","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2506.14919&json=true","fetch_graph":"https://pith.science/api/pith-number/6D2NQDXIHEIZNHDTRRY2GKMRVY/graph.json","fetch_events":"https://pith.science/api/pith-number/6D2NQDXIHEIZNHDTRRY2GKMRVY/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/6D2NQDXIHEIZNHDTRRY2GKMRVY/action/timestamp_anchor","attest_storage":"https://pith.science/pith/6D2NQDXIHEIZNHDTRRY2GKMRVY/action/storage_attestation","attest_author":"https://pith.science/pith/6D2NQDXIHEIZNHDTRRY2GKMRVY/action/author_attestation","sign_citation":"https://pith.science/pith/6D2NQDXIHEIZNHDTRRY2GKMRVY/action/citation_signature","submit_replication":"https://pith.science/pith/6D2NQDXIHEIZNHDTRRY2GKMRVY/action/replication_record"}},"created_at":"2026-07-05T11:23:34.085780+00:00","updated_at":"2026-07-05T11:23:34.085780+00:00"}