{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:PSNV42EO6D2F23BCYKD43SZJQP","short_pith_number":"pith:PSNV42EO","schema_version":"1.0","canonical_sha256":"7c9b5e688ef0f45d6c22c287cdcb2983d5db6e4bdcf415f069f42cd4185f2c96","source":{"kind":"arxiv","id":"2406.19234","version":2},"attestation_state":"computed","paper":{"title":"Generating Is Believing: Membership Inference Attacks against Retrieval-Augmented Generation","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CR","authors_text":"Chen Wang, Gaoyang Liu, Yang Yang, Yuying Li","submitted_at":"2024-06-27T14:58:38Z","abstract_excerpt":"Retrieval-Augmented Generation (RAG) is a state-of-the-art technique that mitigates issues such as hallucinations and knowledge staleness in Large Language Models (LLMs) by retrieving relevant knowledge from an external database to assist in content generation. Existing research has demonstrated potential privacy risks associated with the LLMs of RAG. However, the privacy risks posed by the integration of an external database, which often contains sensitive data such as medical records or personal identities, have remained largely unexplored. In this paper, we aim to bridge this gap by focusin"},"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":"2406.19234","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CR","submitted_at":"2024-06-27T14:58:38Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"24f0c40ddc6ca307379ce9f86293ad2c7ea3561bec170b2d61030b847350caf8","abstract_canon_sha256":"20715e9d200d92187c5266043a6952766c7a79181e986b029354f02c69e61c2d"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T09:12:07.743150Z","signature_b64":"r3KRL7wiZ3fTnX4hYWHcOFPH0YWRdL85mM9SiqOgSAkBCFUpmf74qJnDKJWsqTCUndvlwdu62o5xtdcE7avHCw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"7c9b5e688ef0f45d6c22c287cdcb2983d5db6e4bdcf415f069f42cd4185f2c96","last_reissued_at":"2026-07-05T09:12:07.742664Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T09:12:07.742664Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Generating Is Believing: Membership Inference Attacks against Retrieval-Augmented Generation","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CR","authors_text":"Chen Wang, Gaoyang Liu, Yang Yang, Yuying Li","submitted_at":"2024-06-27T14:58:38Z","abstract_excerpt":"Retrieval-Augmented Generation (RAG) is a state-of-the-art technique that mitigates issues such as hallucinations and knowledge staleness in Large Language Models (LLMs) by retrieving relevant knowledge from an external database to assist in content generation. Existing research has demonstrated potential privacy risks associated with the LLMs of RAG. However, the privacy risks posed by the integration of an external database, which often contains sensitive data such as medical records or personal identities, have remained largely unexplored. In this paper, we aim to bridge this gap by focusin"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2406.19234","kind":"arxiv","version":2},"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/2406.19234/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":"2406.19234","created_at":"2026-07-05T09:12:07.742722+00:00"},{"alias_kind":"arxiv_version","alias_value":"2406.19234v2","created_at":"2026-07-05T09:12:07.742722+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2406.19234","created_at":"2026-07-05T09:12:07.742722+00:00"},{"alias_kind":"pith_short_12","alias_value":"PSNV42EO6D2F","created_at":"2026-07-05T09:12:07.742722+00:00"},{"alias_kind":"pith_short_16","alias_value":"PSNV42EO6D2F23BC","created_at":"2026-07-05T09:12:07.742722+00:00"},{"alias_kind":"pith_short_8","alias_value":"PSNV42EO","created_at":"2026-07-05T09:12:07.742722+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":2,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2605.17034","citing_title":"Privacy Policy Enforcement Guardrails for Data-Sensitive Retrieval-Augmented Generation","ref_index":16,"is_internal_anchor":false},{"citing_arxiv_id":"2605.27825","citing_title":"MRMMIA: Membership Inference Attacks on Memory in Chat Agents","ref_index":11,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/PSNV42EO6D2F23BCYKD43SZJQP","json":"https://pith.science/pith/PSNV42EO6D2F23BCYKD43SZJQP.json","graph_json":"https://pith.science/api/pith-number/PSNV42EO6D2F23BCYKD43SZJQP/graph.json","events_json":"https://pith.science/api/pith-number/PSNV42EO6D2F23BCYKD43SZJQP/events.json","paper":"https://pith.science/paper/PSNV42EO"},"agent_actions":{"view_html":"https://pith.science/pith/PSNV42EO6D2F23BCYKD43SZJQP","download_json":"https://pith.science/pith/PSNV42EO6D2F23BCYKD43SZJQP.json","view_paper":"https://pith.science/paper/PSNV42EO","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2406.19234&json=true","fetch_graph":"https://pith.science/api/pith-number/PSNV42EO6D2F23BCYKD43SZJQP/graph.json","fetch_events":"https://pith.science/api/pith-number/PSNV42EO6D2F23BCYKD43SZJQP/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/PSNV42EO6D2F23BCYKD43SZJQP/action/timestamp_anchor","attest_storage":"https://pith.science/pith/PSNV42EO6D2F23BCYKD43SZJQP/action/storage_attestation","attest_author":"https://pith.science/pith/PSNV42EO6D2F23BCYKD43SZJQP/action/author_attestation","sign_citation":"https://pith.science/pith/PSNV42EO6D2F23BCYKD43SZJQP/action/citation_signature","submit_replication":"https://pith.science/pith/PSNV42EO6D2F23BCYKD43SZJQP/action/replication_record"}},"created_at":"2026-07-05T09:12:07.742722+00:00","updated_at":"2026-07-05T09:12:07.742722+00:00"}