{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:CQXQWBG5PQNHEJD55JY7D3UI3C","short_pith_number":"pith:CQXQWBG5","schema_version":"1.0","canonical_sha256":"142f0b04dd7c1a72247dea71f1ee88d889c6b9972309725125b147a1107cd2d4","source":{"kind":"arxiv","id":"2505.03490","version":1},"attestation_state":"computed","paper":{"title":"A new membership inference attack that spots memorization in generative and predictive models: Loss-Based with Reference Model algorithm (LBRM)","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.LG","authors_text":"Faiz Taleb, Ivan Gazeau, Maryline Laurent","submitted_at":"2025-05-06T12:47:24Z","abstract_excerpt":"Generative models can unintentionally memorize training data, posing significant privacy risks. This paper addresses the memorization phenomenon in time series imputation models, introducing the Loss-Based with Reference Model (LBRM) algorithm. The LBRM method leverages a reference model to enhance the accuracy of membership inference attacks, distinguishing between training and test data. Our contributions are twofold: first, we propose an innovative method to effectively extract and identify memorized training data, significantly improving detection accuracy. On average, without fine-tuning,"},"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":"2505.03490","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2025-05-06T12:47:24Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"31b3004c1542ca730508b983f84b6774ac1c35f8e4fbc34f5b6ca5cd3303de94","abstract_canon_sha256":"26821978995f730ee8368b6ad3a31f9bcc140c32fc6b5424e69d74c338c2746e"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T10:59:16.976767Z","signature_b64":"COQs13ZlX2bdhSDB8ii28eS36MvZy9aYAWCXxVetYpYyeyM8c32Iq9j7XqQNRbrNW7E+KsJB1WA0/sBCIWanCg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"142f0b04dd7c1a72247dea71f1ee88d889c6b9972309725125b147a1107cd2d4","last_reissued_at":"2026-07-05T10:59:16.976328Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T10:59:16.976328Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"A new membership inference attack that spots memorization in generative and predictive models: Loss-Based with Reference Model algorithm (LBRM)","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.LG","authors_text":"Faiz Taleb, Ivan Gazeau, Maryline Laurent","submitted_at":"2025-05-06T12:47:24Z","abstract_excerpt":"Generative models can unintentionally memorize training data, posing significant privacy risks. This paper addresses the memorization phenomenon in time series imputation models, introducing the Loss-Based with Reference Model (LBRM) algorithm. The LBRM method leverages a reference model to enhance the accuracy of membership inference attacks, distinguishing between training and test data. Our contributions are twofold: first, we propose an innovative method to effectively extract and identify memorized training data, significantly improving detection accuracy. On average, without fine-tuning,"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2505.03490","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/2505.03490/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":"2505.03490","created_at":"2026-07-05T10:59:16.976387+00:00"},{"alias_kind":"arxiv_version","alias_value":"2505.03490v1","created_at":"2026-07-05T10:59:16.976387+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2505.03490","created_at":"2026-07-05T10:59:16.976387+00:00"},{"alias_kind":"pith_short_12","alias_value":"CQXQWBG5PQNH","created_at":"2026-07-05T10:59:16.976387+00:00"},{"alias_kind":"pith_short_16","alias_value":"CQXQWBG5PQNHEJD5","created_at":"2026-07-05T10:59:16.976387+00:00"},{"alias_kind":"pith_short_8","alias_value":"CQXQWBG5","created_at":"2026-07-05T10:59:16.976387+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/CQXQWBG5PQNHEJD55JY7D3UI3C","json":"https://pith.science/pith/CQXQWBG5PQNHEJD55JY7D3UI3C.json","graph_json":"https://pith.science/api/pith-number/CQXQWBG5PQNHEJD55JY7D3UI3C/graph.json","events_json":"https://pith.science/api/pith-number/CQXQWBG5PQNHEJD55JY7D3UI3C/events.json","paper":"https://pith.science/paper/CQXQWBG5"},"agent_actions":{"view_html":"https://pith.science/pith/CQXQWBG5PQNHEJD55JY7D3UI3C","download_json":"https://pith.science/pith/CQXQWBG5PQNHEJD55JY7D3UI3C.json","view_paper":"https://pith.science/paper/CQXQWBG5","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2505.03490&json=true","fetch_graph":"https://pith.science/api/pith-number/CQXQWBG5PQNHEJD55JY7D3UI3C/graph.json","fetch_events":"https://pith.science/api/pith-number/CQXQWBG5PQNHEJD55JY7D3UI3C/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/CQXQWBG5PQNHEJD55JY7D3UI3C/action/timestamp_anchor","attest_storage":"https://pith.science/pith/CQXQWBG5PQNHEJD55JY7D3UI3C/action/storage_attestation","attest_author":"https://pith.science/pith/CQXQWBG5PQNHEJD55JY7D3UI3C/action/author_attestation","sign_citation":"https://pith.science/pith/CQXQWBG5PQNHEJD55JY7D3UI3C/action/citation_signature","submit_replication":"https://pith.science/pith/CQXQWBG5PQNHEJD55JY7D3UI3C/action/replication_record"}},"created_at":"2026-07-05T10:59:16.976387+00:00","updated_at":"2026-07-05T10:59:16.976387+00:00"}