{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:ZSM32HDKYTW7G5KNZYLJQHJRUI","short_pith_number":"pith:ZSM32HDK","schema_version":"1.0","canonical_sha256":"cc99bd1c6ac4edf3754dce16981d31a209d9302a05eea0a122053b45626fdb33","source":{"kind":"arxiv","id":"2408.05212","version":2},"attestation_state":"computed","paper":{"title":"Preserving Privacy in Large Language Models: A Survey on Current Threats and Solutions","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.CL","cs.LG"],"primary_cat":"cs.CR","authors_text":"Andrea Santilli, Elena Sofia Ruzzetti, Emanuele Rodol\\`a, Fabio Massimo Zanzotto, Michele Miranda, S\\'ebastien Brati\\`eres","submitted_at":"2024-08-10T05:41:19Z","abstract_excerpt":"Large Language Models (LLMs) represent a significant advancement in artificial intelligence, finding applications across various domains. However, their reliance on massive internet-sourced datasets for training brings notable privacy issues, which are exacerbated in critical domains (e.g., healthcare). Moreover, certain application-specific scenarios may require fine-tuning these models on private data. This survey critically examines the privacy threats associated with LLMs, emphasizing the potential for these models to memorize and inadvertently reveal sensitive information. We explore curr"},"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":"2408.05212","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CR","submitted_at":"2024-08-10T05:41:19Z","cross_cats_sorted":["cs.AI","cs.CL","cs.LG"],"title_canon_sha256":"6f1ed0948196ec0e255c3b26d0005d4d8944788442676cffbd5c19227408f34a","abstract_canon_sha256":"bcd9a448aed4a0ef2c38c57966ffb1413c86dbeb27d32b111b00adc80f9940ce"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T10:12:00.507114Z","signature_b64":"9pnqnkoW4u5qGJ4ZTcT6yqXsDSgwvp9WR5O3m370xVea3w6A0v08f6c4IDWSsHuVT+7k5gjKEMcxr4f7JittBw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"cc99bd1c6ac4edf3754dce16981d31a209d9302a05eea0a122053b45626fdb33","last_reissued_at":"2026-07-05T10:12:00.506554Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T10:12:00.506554Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Preserving Privacy in Large Language Models: A Survey on Current Threats and Solutions","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.CL","cs.LG"],"primary_cat":"cs.CR","authors_text":"Andrea Santilli, Elena Sofia Ruzzetti, Emanuele Rodol\\`a, Fabio Massimo Zanzotto, Michele Miranda, S\\'ebastien Brati\\`eres","submitted_at":"2024-08-10T05:41:19Z","abstract_excerpt":"Large Language Models (LLMs) represent a significant advancement in artificial intelligence, finding applications across various domains. However, their reliance on massive internet-sourced datasets for training brings notable privacy issues, which are exacerbated in critical domains (e.g., healthcare). Moreover, certain application-specific scenarios may require fine-tuning these models on private data. This survey critically examines the privacy threats associated with LLMs, emphasizing the potential for these models to memorize and inadvertently reveal sensitive information. We explore curr"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2408.05212","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/2408.05212/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":"2408.05212","created_at":"2026-07-05T10:12:00.506615+00:00"},{"alias_kind":"arxiv_version","alias_value":"2408.05212v2","created_at":"2026-07-05T10:12:00.506615+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2408.05212","created_at":"2026-07-05T10:12:00.506615+00:00"},{"alias_kind":"pith_short_12","alias_value":"ZSM32HDKYTW7","created_at":"2026-07-05T10:12:00.506615+00:00"},{"alias_kind":"pith_short_16","alias_value":"ZSM32HDKYTW7G5KN","created_at":"2026-07-05T10:12:00.506615+00:00"},{"alias_kind":"pith_short_8","alias_value":"ZSM32HDK","created_at":"2026-07-05T10:12:00.506615+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2606.08311","citing_title":"Curation of a Cardiology Interface Terminology for Highlighting Electronic Health Records using Machine Learning","ref_index":50,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/ZSM32HDKYTW7G5KNZYLJQHJRUI","json":"https://pith.science/pith/ZSM32HDKYTW7G5KNZYLJQHJRUI.json","graph_json":"https://pith.science/api/pith-number/ZSM32HDKYTW7G5KNZYLJQHJRUI/graph.json","events_json":"https://pith.science/api/pith-number/ZSM32HDKYTW7G5KNZYLJQHJRUI/events.json","paper":"https://pith.science/paper/ZSM32HDK"},"agent_actions":{"view_html":"https://pith.science/pith/ZSM32HDKYTW7G5KNZYLJQHJRUI","download_json":"https://pith.science/pith/ZSM32HDKYTW7G5KNZYLJQHJRUI.json","view_paper":"https://pith.science/paper/ZSM32HDK","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2408.05212&json=true","fetch_graph":"https://pith.science/api/pith-number/ZSM32HDKYTW7G5KNZYLJQHJRUI/graph.json","fetch_events":"https://pith.science/api/pith-number/ZSM32HDKYTW7G5KNZYLJQHJRUI/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/ZSM32HDKYTW7G5KNZYLJQHJRUI/action/timestamp_anchor","attest_storage":"https://pith.science/pith/ZSM32HDKYTW7G5KNZYLJQHJRUI/action/storage_attestation","attest_author":"https://pith.science/pith/ZSM32HDKYTW7G5KNZYLJQHJRUI/action/author_attestation","sign_citation":"https://pith.science/pith/ZSM32HDKYTW7G5KNZYLJQHJRUI/action/citation_signature","submit_replication":"https://pith.science/pith/ZSM32HDKYTW7G5KNZYLJQHJRUI/action/replication_record"}},"created_at":"2026-07-05T10:12:00.506615+00:00","updated_at":"2026-07-05T10:12:00.506615+00:00"}