{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:JKVUB2PI75SB2HXD37MK7Z5I34","short_pith_number":"pith:JKVUB2PI","schema_version":"1.0","canonical_sha256":"4aab40e9e8ff641d1ee3dfd8afe7a8df23f884d5097c1864684f792bc537ac55","source":{"kind":"arxiv","id":"2508.06087","version":1},"attestation_state":"computed","paper":{"title":"Adaptive Backtracking for Privacy Protection in Large Language Models","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.LG","stat.ML"],"primary_cat":"cs.CR","authors_text":"Bo Li, Weitao Ma, Xiachong Feng, Xiaocheng Feng, Yuxuan Gu, Zhihao Yao","submitted_at":"2025-08-08T07:29:33Z","abstract_excerpt":"The preservation of privacy has emerged as a critical topic in the era of artificial intelligence. However, current work focuses on user-oriented privacy, overlooking severe enterprise data leakage risks exacerbated by the Retrieval-Augmented Generation paradigm. To address this gap, our paper introduces a novel objective: enterprise-oriented privacy concerns. Achieving this objective requires overcoming two fundamental challenges: existing methods such as data sanitization severely degrade model performance, and the field lacks public datasets for evaluation. We address these challenges with "},"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":"2508.06087","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CR","submitted_at":"2025-08-08T07:29:33Z","cross_cats_sorted":["cs.LG","stat.ML"],"title_canon_sha256":"9af12f70335f216a7ff8f1ced7f26a708047f1c26edc3892fddb359c06b6e877","abstract_canon_sha256":"ee082a7bcb29cd024e5f9bdfeb8309f36512166cbbce3799102361c1432eb559"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:50:49.413789Z","signature_b64":"dbQ32S2WQU/gdNpyNwo356jSu/UsaLEqhMMlwy9vhus7inDyVPL+8Lig4CKmECUMQZCe7+AlQ86QFZ2fGQCRAg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"4aab40e9e8ff641d1ee3dfd8afe7a8df23f884d5097c1864684f792bc537ac55","last_reissued_at":"2026-07-05T11:50:49.413300Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:50:49.413300Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Adaptive Backtracking for Privacy Protection in Large Language Models","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.LG","stat.ML"],"primary_cat":"cs.CR","authors_text":"Bo Li, Weitao Ma, Xiachong Feng, Xiaocheng Feng, Yuxuan Gu, Zhihao Yao","submitted_at":"2025-08-08T07:29:33Z","abstract_excerpt":"The preservation of privacy has emerged as a critical topic in the era of artificial intelligence. However, current work focuses on user-oriented privacy, overlooking severe enterprise data leakage risks exacerbated by the Retrieval-Augmented Generation paradigm. To address this gap, our paper introduces a novel objective: enterprise-oriented privacy concerns. Achieving this objective requires overcoming two fundamental challenges: existing methods such as data sanitization severely degrade model performance, and the field lacks public datasets for evaluation. We address these challenges with "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2508.06087","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/2508.06087/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":"2508.06087","created_at":"2026-07-05T11:50:49.413360+00:00"},{"alias_kind":"arxiv_version","alias_value":"2508.06087v1","created_at":"2026-07-05T11:50:49.413360+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2508.06087","created_at":"2026-07-05T11:50:49.413360+00:00"},{"alias_kind":"pith_short_12","alias_value":"JKVUB2PI75SB","created_at":"2026-07-05T11:50:49.413360+00:00"},{"alias_kind":"pith_short_16","alias_value":"JKVUB2PI75SB2HXD","created_at":"2026-07-05T11:50:49.413360+00:00"},{"alias_kind":"pith_short_8","alias_value":"JKVUB2PI","created_at":"2026-07-05T11:50:49.413360+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/JKVUB2PI75SB2HXD37MK7Z5I34","json":"https://pith.science/pith/JKVUB2PI75SB2HXD37MK7Z5I34.json","graph_json":"https://pith.science/api/pith-number/JKVUB2PI75SB2HXD37MK7Z5I34/graph.json","events_json":"https://pith.science/api/pith-number/JKVUB2PI75SB2HXD37MK7Z5I34/events.json","paper":"https://pith.science/paper/JKVUB2PI"},"agent_actions":{"view_html":"https://pith.science/pith/JKVUB2PI75SB2HXD37MK7Z5I34","download_json":"https://pith.science/pith/JKVUB2PI75SB2HXD37MK7Z5I34.json","view_paper":"https://pith.science/paper/JKVUB2PI","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2508.06087&json=true","fetch_graph":"https://pith.science/api/pith-number/JKVUB2PI75SB2HXD37MK7Z5I34/graph.json","fetch_events":"https://pith.science/api/pith-number/JKVUB2PI75SB2HXD37MK7Z5I34/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/JKVUB2PI75SB2HXD37MK7Z5I34/action/timestamp_anchor","attest_storage":"https://pith.science/pith/JKVUB2PI75SB2HXD37MK7Z5I34/action/storage_attestation","attest_author":"https://pith.science/pith/JKVUB2PI75SB2HXD37MK7Z5I34/action/author_attestation","sign_citation":"https://pith.science/pith/JKVUB2PI75SB2HXD37MK7Z5I34/action/citation_signature","submit_replication":"https://pith.science/pith/JKVUB2PI75SB2HXD37MK7Z5I34/action/replication_record"}},"created_at":"2026-07-05T11:50:49.413360+00:00","updated_at":"2026-07-05T11:50:49.413360+00:00"}