{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:MCBYWFJEB2GC7OUJA6ZCECQUTF","short_pith_number":"pith:MCBYWFJE","schema_version":"1.0","canonical_sha256":"60838b15240e8c2fba8907b2220a149973f355e4dd2ffba81b97081855a61514","source":{"kind":"arxiv","id":"2402.16893","version":1},"attestation_state":"computed","paper":{"title":"The Good and The Bad: Exploring Privacy Issues in Retrieval-Augmented Generation (RAG)","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.CL"],"primary_cat":"cs.CR","authors_text":"Dawei Yin, Han Xu, Jiankun Zhang, Jie Ren, Jiliang Tang, Pengfei He, Shenglai Zeng, Shuaiqiang Wang, Yi Chang, Yiding Liu, Yue Xing","submitted_at":"2024-02-23T18:35:15Z","abstract_excerpt":"Retrieval-augmented generation (RAG) is a powerful technique to facilitate language model with proprietary and private data, where data privacy is a pivotal concern. Whereas extensive research has demonstrated the privacy risks of large language models (LLMs), the RAG technique could potentially reshape the inherent behaviors of LLM generation, posing new privacy issues that are currently under-explored. In this work, we conduct extensive empirical studies with novel attack methods, which demonstrate the vulnerability of RAG systems on leaking the private retrieval database. Despite the new ri"},"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":"2402.16893","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CR","submitted_at":"2024-02-23T18:35:15Z","cross_cats_sorted":["cs.AI","cs.CL"],"title_canon_sha256":"7cb71b87cdf8ac54cd69decaf22b63a950cf0c23408ad0851c2269271da9eb36","abstract_canon_sha256":"e57d4f5884c2da0758afc9a706243255a75c698a37a823f12e4022e7ada451d9"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T07:50:46.184645Z","signature_b64":"QDT+cNOaJgZUHNJVt1VMwoggcI7XamXaJlhL1LSU/BI7mkiqdkH9Q7U/CyWuI/qvArbu+v+FBO6i9RSB6n1gAQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"60838b15240e8c2fba8907b2220a149973f355e4dd2ffba81b97081855a61514","last_reissued_at":"2026-07-05T07:50:46.184176Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T07:50:46.184176Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"The Good and The Bad: Exploring Privacy Issues in Retrieval-Augmented Generation (RAG)","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.CL"],"primary_cat":"cs.CR","authors_text":"Dawei Yin, Han Xu, Jiankun Zhang, Jie Ren, Jiliang Tang, Pengfei He, Shenglai Zeng, Shuaiqiang Wang, Yi Chang, Yiding Liu, Yue Xing","submitted_at":"2024-02-23T18:35:15Z","abstract_excerpt":"Retrieval-augmented generation (RAG) is a powerful technique to facilitate language model with proprietary and private data, where data privacy is a pivotal concern. Whereas extensive research has demonstrated the privacy risks of large language models (LLMs), the RAG technique could potentially reshape the inherent behaviors of LLM generation, posing new privacy issues that are currently under-explored. In this work, we conduct extensive empirical studies with novel attack methods, which demonstrate the vulnerability of RAG systems on leaking the private retrieval database. Despite the new ri"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2402.16893","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/2402.16893/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":"2402.16893","created_at":"2026-07-05T07:50:46.184233+00:00"},{"alias_kind":"arxiv_version","alias_value":"2402.16893v1","created_at":"2026-07-05T07:50:46.184233+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2402.16893","created_at":"2026-07-05T07:50:46.184233+00:00"},{"alias_kind":"pith_short_12","alias_value":"MCBYWFJEB2GC","created_at":"2026-07-05T07:50:46.184233+00:00"},{"alias_kind":"pith_short_16","alias_value":"MCBYWFJEB2GC7OUJ","created_at":"2026-07-05T07:50:46.184233+00:00"},{"alias_kind":"pith_short_8","alias_value":"MCBYWFJE","created_at":"2026-07-05T07:50:46.184233+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":6,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2606.26627","citing_title":"Agents That Know Too Much: A Data-Centric Survey of Privacy in LLM Agents","ref_index":124,"is_internal_anchor":false},{"citing_arxiv_id":"2605.27825","citing_title":"MRMMIA: Membership Inference Attacks on Memory in Chat Agents","ref_index":31,"is_internal_anchor":false},{"citing_arxiv_id":"2409.10102","citing_title":"Trustworthiness in Retrieval-Augmented Generation Systems: A Survey","ref_index":85,"is_internal_anchor":false},{"citing_arxiv_id":"2604.26525","citing_title":"PRAG: End-to-End Privacy-Preserving Retrieval-Augmented Generation","ref_index":38,"is_internal_anchor":false},{"citing_arxiv_id":"2604.08046","citing_title":"Guaranteeing Knowledge Integration with Joint Decoding for Retrieval-Augmented Generation","ref_index":6,"is_internal_anchor":false},{"citing_arxiv_id":"2604.09747","citing_title":"ADAM: A Systematic Data Extraction Attack on Agent Memory via Adaptive Querying","ref_index":25,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/MCBYWFJEB2GC7OUJA6ZCECQUTF","json":"https://pith.science/pith/MCBYWFJEB2GC7OUJA6ZCECQUTF.json","graph_json":"https://pith.science/api/pith-number/MCBYWFJEB2GC7OUJA6ZCECQUTF/graph.json","events_json":"https://pith.science/api/pith-number/MCBYWFJEB2GC7OUJA6ZCECQUTF/events.json","paper":"https://pith.science/paper/MCBYWFJE"},"agent_actions":{"view_html":"https://pith.science/pith/MCBYWFJEB2GC7OUJA6ZCECQUTF","download_json":"https://pith.science/pith/MCBYWFJEB2GC7OUJA6ZCECQUTF.json","view_paper":"https://pith.science/paper/MCBYWFJE","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2402.16893&json=true","fetch_graph":"https://pith.science/api/pith-number/MCBYWFJEB2GC7OUJA6ZCECQUTF/graph.json","fetch_events":"https://pith.science/api/pith-number/MCBYWFJEB2GC7OUJA6ZCECQUTF/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/MCBYWFJEB2GC7OUJA6ZCECQUTF/action/timestamp_anchor","attest_storage":"https://pith.science/pith/MCBYWFJEB2GC7OUJA6ZCECQUTF/action/storage_attestation","attest_author":"https://pith.science/pith/MCBYWFJEB2GC7OUJA6ZCECQUTF/action/author_attestation","sign_citation":"https://pith.science/pith/MCBYWFJEB2GC7OUJA6ZCECQUTF/action/citation_signature","submit_replication":"https://pith.science/pith/MCBYWFJEB2GC7OUJA6ZCECQUTF/action/replication_record"}},"created_at":"2026-07-05T07:50:46.184233+00:00","updated_at":"2026-07-05T07:50:46.184233+00:00"}