{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:RHEVDSBS3QTBOHZJNECDPACAAC","short_pith_number":"pith:RHEVDSBS","schema_version":"1.0","canonical_sha256":"89c951c832dc26171f29690437804000b0c110658248165ad3d2640536b40fdc","source":{"kind":"arxiv","id":"2503.15548","version":1},"attestation_state":"computed","paper":{"title":"Privacy-Aware RAG: Secure and Isolated Knowledge Retrieval","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CR","authors_text":"Pengcheng Zhou, Yinglun Feng, Zhongliang Yang","submitted_at":"2025-03-17T07:45:05Z","abstract_excerpt":"The widespread adoption of Retrieval-Augmented Generation (RAG) systems in real-world applications has heightened concerns about the confidentiality and integrity of their proprietary knowledge bases. These knowledge bases, which play a critical role in enhancing the generative capabilities of Large Language Models (LLMs), are increasingly vulnerable to breaches that could compromise sensitive information. To address these challenges, this paper proposes an advanced encryption methodology designed to protect RAG systems from unauthorized access and data leakage. Our approach encrypts both text"},"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":"2503.15548","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CR","submitted_at":"2025-03-17T07:45:05Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"3a35d0bdf503f0b0e5c59f529ca26ec8a18824ca1fe6cb36ca551bbe5303d298","abstract_canon_sha256":"df64d563fdc1de2c2641de96fc07aba9843511682f8712361e18cb26c20252a4"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T10:35:52.556554Z","signature_b64":"pjsTRrvwFBQpopOtiDPRFNwdm0Iex3hrfV6kefPYLmMUU/rebwuXGjKlGoAXARrL8zIkoRNYjwytUNEJnun1BA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"89c951c832dc26171f29690437804000b0c110658248165ad3d2640536b40fdc","last_reissued_at":"2026-07-05T10:35:52.555523Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T10:35:52.555523Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Privacy-Aware RAG: Secure and Isolated Knowledge Retrieval","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CR","authors_text":"Pengcheng Zhou, Yinglun Feng, Zhongliang Yang","submitted_at":"2025-03-17T07:45:05Z","abstract_excerpt":"The widespread adoption of Retrieval-Augmented Generation (RAG) systems in real-world applications has heightened concerns about the confidentiality and integrity of their proprietary knowledge bases. These knowledge bases, which play a critical role in enhancing the generative capabilities of Large Language Models (LLMs), are increasingly vulnerable to breaches that could compromise sensitive information. To address these challenges, this paper proposes an advanced encryption methodology designed to protect RAG systems from unauthorized access and data leakage. Our approach encrypts both text"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2503.15548","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/2503.15548/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":"2503.15548","created_at":"2026-07-05T10:35:52.555682+00:00"},{"alias_kind":"arxiv_version","alias_value":"2503.15548v1","created_at":"2026-07-05T10:35:52.555682+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2503.15548","created_at":"2026-07-05T10:35:52.555682+00:00"},{"alias_kind":"pith_short_12","alias_value":"RHEVDSBS3QTB","created_at":"2026-07-05T10:35:52.555682+00:00"},{"alias_kind":"pith_short_16","alias_value":"RHEVDSBS3QTBOHZJ","created_at":"2026-07-05T10:35:52.555682+00:00"},{"alias_kind":"pith_short_8","alias_value":"RHEVDSBS","created_at":"2026-07-05T10:35:52.555682+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":4,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2606.24623","citing_title":"Privacy-Preserving RAG via Multi-Agent Semantic Rewriting: Achieving Confidentiality Without Compromising Contextual Fidelity","ref_index":26,"is_internal_anchor":false},{"citing_arxiv_id":"2606.22153","citing_title":"$\\pi$-RAG: Oblivious Retrieval via Semantic Quantization and Transcendental Addressing for Large Language Models","ref_index":6,"is_internal_anchor":false},{"citing_arxiv_id":"2603.09002","citing_title":"Security Considerations for Multi-agent Systems","ref_index":257,"is_internal_anchor":false},{"citing_arxiv_id":"2604.26525","citing_title":"PRAG: End-to-End Privacy-Preserving Retrieval-Augmented Generation","ref_index":42,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/RHEVDSBS3QTBOHZJNECDPACAAC","json":"https://pith.science/pith/RHEVDSBS3QTBOHZJNECDPACAAC.json","graph_json":"https://pith.science/api/pith-number/RHEVDSBS3QTBOHZJNECDPACAAC/graph.json","events_json":"https://pith.science/api/pith-number/RHEVDSBS3QTBOHZJNECDPACAAC/events.json","paper":"https://pith.science/paper/RHEVDSBS"},"agent_actions":{"view_html":"https://pith.science/pith/RHEVDSBS3QTBOHZJNECDPACAAC","download_json":"https://pith.science/pith/RHEVDSBS3QTBOHZJNECDPACAAC.json","view_paper":"https://pith.science/paper/RHEVDSBS","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2503.15548&json=true","fetch_graph":"https://pith.science/api/pith-number/RHEVDSBS3QTBOHZJNECDPACAAC/graph.json","fetch_events":"https://pith.science/api/pith-number/RHEVDSBS3QTBOHZJNECDPACAAC/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/RHEVDSBS3QTBOHZJNECDPACAAC/action/timestamp_anchor","attest_storage":"https://pith.science/pith/RHEVDSBS3QTBOHZJNECDPACAAC/action/storage_attestation","attest_author":"https://pith.science/pith/RHEVDSBS3QTBOHZJNECDPACAAC/action/author_attestation","sign_citation":"https://pith.science/pith/RHEVDSBS3QTBOHZJNECDPACAAC/action/citation_signature","submit_replication":"https://pith.science/pith/RHEVDSBS3QTBOHZJNECDPACAAC/action/replication_record"}},"created_at":"2026-07-05T10:35:52.555682+00:00","updated_at":"2026-07-05T10:35:52.555682+00:00"}