{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:KO7ZRBBPKTNUMFAXLHXRM4FGSQ","short_pith_number":"pith:KO7ZRBBP","schema_version":"1.0","canonical_sha256":"53bf98842f54db46141759ef1670a6943a196ea3f93d7f7f76ffe5e0ce16076d","source":{"kind":"arxiv","id":"2410.20142","version":2},"attestation_state":"computed","paper":{"title":"Mask-based Membership Inference Attacks for Retrieval-Augmented Generation","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI","cs.IR"],"primary_cat":"cs.CR","authors_text":"Cheng Long, Mingrui Liu, Sixiao Zhang","submitted_at":"2024-10-26T10:43:39Z","abstract_excerpt":"Retrieval-Augmented Generation (RAG) has been an effective approach to mitigate hallucinations in large language models (LLMs) by incorporating up-to-date and domain-specific knowledge. Recently, there has been a trend of storing up-to-date or copyrighted data in RAG knowledge databases instead of using it for LLM training. This practice has raised concerns about Membership Inference Attacks (MIAs), which aim to detect if a specific target document is stored in the RAG system's knowledge database so as to protect the rights of data producers. While research has focused on enhancing the trustwo"},"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":"2410.20142","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CR","submitted_at":"2024-10-26T10:43:39Z","cross_cats_sorted":["cs.AI","cs.IR"],"title_canon_sha256":"8be1f6d497a9e113bb8bdd3fb29570617bc60752a03fee38c6effd2a69b02884","abstract_canon_sha256":"e7c05709f3e636cecc81b0660a4c01120a14a04563251cb6bb021f37e6632e75"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T10:11:27.562776Z","signature_b64":"K+sFZvjkfXXktF8VSjt1dVsKKDajTIHIlIIWZkHxO1zeYkTCEd0qu76P8BweeCnKrtJipI9PpAPSJxjJW7KpCg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"53bf98842f54db46141759ef1670a6943a196ea3f93d7f7f76ffe5e0ce16076d","last_reissued_at":"2026-07-05T10:11:27.562206Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T10:11:27.562206Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Mask-based Membership Inference Attacks for Retrieval-Augmented Generation","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI","cs.IR"],"primary_cat":"cs.CR","authors_text":"Cheng Long, Mingrui Liu, Sixiao Zhang","submitted_at":"2024-10-26T10:43:39Z","abstract_excerpt":"Retrieval-Augmented Generation (RAG) has been an effective approach to mitigate hallucinations in large language models (LLMs) by incorporating up-to-date and domain-specific knowledge. Recently, there has been a trend of storing up-to-date or copyrighted data in RAG knowledge databases instead of using it for LLM training. This practice has raised concerns about Membership Inference Attacks (MIAs), which aim to detect if a specific target document is stored in the RAG system's knowledge database so as to protect the rights of data producers. While research has focused on enhancing the trustwo"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2410.20142","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/2410.20142/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":"2410.20142","created_at":"2026-07-05T10:11:27.562277+00:00"},{"alias_kind":"arxiv_version","alias_value":"2410.20142v2","created_at":"2026-07-05T10:11:27.562277+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2410.20142","created_at":"2026-07-05T10:11:27.562277+00:00"},{"alias_kind":"pith_short_12","alias_value":"KO7ZRBBPKTNU","created_at":"2026-07-05T10:11:27.562277+00:00"},{"alias_kind":"pith_short_16","alias_value":"KO7ZRBBPKTNUMFAX","created_at":"2026-07-05T10:11:27.562277+00:00"},{"alias_kind":"pith_short_8","alias_value":"KO7ZRBBP","created_at":"2026-07-05T10:11:27.562277+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2605.27825","citing_title":"MRMMIA: Membership Inference Attacks on Memory in Chat Agents","ref_index":12,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/KO7ZRBBPKTNUMFAXLHXRM4FGSQ","json":"https://pith.science/pith/KO7ZRBBPKTNUMFAXLHXRM4FGSQ.json","graph_json":"https://pith.science/api/pith-number/KO7ZRBBPKTNUMFAXLHXRM4FGSQ/graph.json","events_json":"https://pith.science/api/pith-number/KO7ZRBBPKTNUMFAXLHXRM4FGSQ/events.json","paper":"https://pith.science/paper/KO7ZRBBP"},"agent_actions":{"view_html":"https://pith.science/pith/KO7ZRBBPKTNUMFAXLHXRM4FGSQ","download_json":"https://pith.science/pith/KO7ZRBBPKTNUMFAXLHXRM4FGSQ.json","view_paper":"https://pith.science/paper/KO7ZRBBP","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2410.20142&json=true","fetch_graph":"https://pith.science/api/pith-number/KO7ZRBBPKTNUMFAXLHXRM4FGSQ/graph.json","fetch_events":"https://pith.science/api/pith-number/KO7ZRBBPKTNUMFAXLHXRM4FGSQ/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/KO7ZRBBPKTNUMFAXLHXRM4FGSQ/action/timestamp_anchor","attest_storage":"https://pith.science/pith/KO7ZRBBPKTNUMFAXLHXRM4FGSQ/action/storage_attestation","attest_author":"https://pith.science/pith/KO7ZRBBPKTNUMFAXLHXRM4FGSQ/action/author_attestation","sign_citation":"https://pith.science/pith/KO7ZRBBPKTNUMFAXLHXRM4FGSQ/action/citation_signature","submit_replication":"https://pith.science/pith/KO7ZRBBPKTNUMFAXLHXRM4FGSQ/action/replication_record"}},"created_at":"2026-07-05T10:11:27.562277+00:00","updated_at":"2026-07-05T10:11:27.562277+00:00"}