{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:FJZMYPDFYWCUZVFOEZY2BTMJVS","short_pith_number":"pith:FJZMYPDF","schema_version":"1.0","canonical_sha256":"2a72cc3c65c5854cd4ae2671a0cd89aca4db68de90bfc8fee1fad23d49018779","source":{"kind":"arxiv","id":"2505.01976","version":1},"attestation_state":"computed","paper":{"title":"A Survey on Privacy Risks and Protection in Large Language Models","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CR","authors_text":"Kang Chen, Li Shen, Pengcheng Wu, Shibo Feng, Xiuze Zhou, Yuanguo Lin","submitted_at":"2025-05-04T03:04:07Z","abstract_excerpt":"Although Large Language Models (LLMs) have become increasingly integral to diverse applications, their capabilities raise significant privacy concerns. This survey offers a comprehensive overview of privacy risks associated with LLMs and examines current solutions to mitigate these challenges. First, we analyze privacy leakage and attacks in LLMs, focusing on how these models unintentionally expose sensitive information through techniques such as model inversion, training data extraction, and membership inference. We investigate the mechanisms of privacy leakage, including the unauthorized ext"},"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":"2505.01976","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CR","submitted_at":"2025-05-04T03:04:07Z","cross_cats_sorted":[],"title_canon_sha256":"2f6a5bc7944b6c61353ad4662b2db8fe031d4a73d21bf52c54014a2eb249332e","abstract_canon_sha256":"669de1ed68eb45d390f3ff640ab0d9f18c58a471ad06c3414bc50d5a67d6b411"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T10:58:29.562501Z","signature_b64":"Ru+9mCFgGprVfdy9YFMRiROVHg7hcsiHIoCTXuD17r6fK/o1ja/e9fkLF+fpIIcpZx4T2Kq4bppRqfGlGk+1CA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"2a72cc3c65c5854cd4ae2671a0cd89aca4db68de90bfc8fee1fad23d49018779","last_reissued_at":"2026-07-05T10:58:29.561971Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T10:58:29.561971Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"A Survey on Privacy Risks and Protection in Large Language Models","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CR","authors_text":"Kang Chen, Li Shen, Pengcheng Wu, Shibo Feng, Xiuze Zhou, Yuanguo Lin","submitted_at":"2025-05-04T03:04:07Z","abstract_excerpt":"Although Large Language Models (LLMs) have become increasingly integral to diverse applications, their capabilities raise significant privacy concerns. This survey offers a comprehensive overview of privacy risks associated with LLMs and examines current solutions to mitigate these challenges. First, we analyze privacy leakage and attacks in LLMs, focusing on how these models unintentionally expose sensitive information through techniques such as model inversion, training data extraction, and membership inference. We investigate the mechanisms of privacy leakage, including the unauthorized ext"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2505.01976","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/2505.01976/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":"2505.01976","created_at":"2026-07-05T10:58:29.562042+00:00"},{"alias_kind":"arxiv_version","alias_value":"2505.01976v1","created_at":"2026-07-05T10:58:29.562042+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2505.01976","created_at":"2026-07-05T10:58:29.562042+00:00"},{"alias_kind":"pith_short_12","alias_value":"FJZMYPDFYWCU","created_at":"2026-07-05T10:58:29.562042+00:00"},{"alias_kind":"pith_short_16","alias_value":"FJZMYPDFYWCUZVFO","created_at":"2026-07-05T10:58:29.562042+00:00"},{"alias_kind":"pith_short_8","alias_value":"FJZMYPDF","created_at":"2026-07-05T10:58:29.562042+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":3,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2510.04905","citing_title":"Retrieval-Augmented Code Generation: A Survey with Focus on Repository-Level Approaches","ref_index":16,"is_internal_anchor":false},{"citing_arxiv_id":"2605.10614","citing_title":"PRISM: Generation-Time Detection and Mitigation of Secret Leakage in Multi-Agent LLM Pipelines","ref_index":32,"is_internal_anchor":false},{"citing_arxiv_id":"2604.09952","citing_title":"SLM Finetuning for Natural Language to Domain Specific Code Generation in Production","ref_index":6,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/FJZMYPDFYWCUZVFOEZY2BTMJVS","json":"https://pith.science/pith/FJZMYPDFYWCUZVFOEZY2BTMJVS.json","graph_json":"https://pith.science/api/pith-number/FJZMYPDFYWCUZVFOEZY2BTMJVS/graph.json","events_json":"https://pith.science/api/pith-number/FJZMYPDFYWCUZVFOEZY2BTMJVS/events.json","paper":"https://pith.science/paper/FJZMYPDF"},"agent_actions":{"view_html":"https://pith.science/pith/FJZMYPDFYWCUZVFOEZY2BTMJVS","download_json":"https://pith.science/pith/FJZMYPDFYWCUZVFOEZY2BTMJVS.json","view_paper":"https://pith.science/paper/FJZMYPDF","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2505.01976&json=true","fetch_graph":"https://pith.science/api/pith-number/FJZMYPDFYWCUZVFOEZY2BTMJVS/graph.json","fetch_events":"https://pith.science/api/pith-number/FJZMYPDFYWCUZVFOEZY2BTMJVS/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/FJZMYPDFYWCUZVFOEZY2BTMJVS/action/timestamp_anchor","attest_storage":"https://pith.science/pith/FJZMYPDFYWCUZVFOEZY2BTMJVS/action/storage_attestation","attest_author":"https://pith.science/pith/FJZMYPDFYWCUZVFOEZY2BTMJVS/action/author_attestation","sign_citation":"https://pith.science/pith/FJZMYPDFYWCUZVFOEZY2BTMJVS/action/citation_signature","submit_replication":"https://pith.science/pith/FJZMYPDFYWCUZVFOEZY2BTMJVS/action/replication_record"}},"created_at":"2026-07-05T10:58:29.562042+00:00","updated_at":"2026-07-05T10:58:29.562042+00:00"}