{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:LLM55LWBED6USG4C4ELVPZC7EE","short_pith_number":"pith:LLM55LWB","schema_version":"1.0","canonical_sha256":"5ad9deaec120fd491b82e11757e45f21074e391cd576f292c7f925bbc6802e9f","source":{"kind":"arxiv","id":"2502.05224","version":1},"attestation_state":"computed","paper":{"title":"A Survey on Backdoor Threats in Large Language Models (LLMs): Attacks, Defenses, and Evaluations","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CR","authors_text":"Qingchuan Zhao, Tao Ni, Wei-Bin Lee, Yihe Zhou","submitted_at":"2025-02-06T04:43:05Z","abstract_excerpt":"Large Language Models (LLMs) have achieved significantly advanced capabilities in understanding and generating human language text, which have gained increasing popularity over recent years. Apart from their state-of-the-art natural language processing (NLP) performance, considering their widespread usage in many industries, including medicine, finance, education, etc., security concerns over their usage grow simultaneously. In recent years, the evolution of backdoor attacks has progressed with the advancement of defense mechanisms against them and more well-developed features in the LLMs. In "},"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":"2502.05224","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CR","submitted_at":"2025-02-06T04:43:05Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"bd9fc03fe38ce3dd8f88717d626d1a3d61d517cff3f4df2461af91decafc03aa","abstract_canon_sha256":"ac7208b5d722396b909d0180ff4fde2c892d33aa7b6ce72a79cb7650be1ca7cd"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T10:11:34.379669Z","signature_b64":"7S8aFWYNzSA2PPcjYwQ9zO7GsOFer08VcDQ6CXkSojxKJvRThsIrkvWbYOtnuW8ZofhkYzCaVAZlzb/EAqo1Dw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"5ad9deaec120fd491b82e11757e45f21074e391cd576f292c7f925bbc6802e9f","last_reissued_at":"2026-07-05T10:11:34.379208Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T10:11:34.379208Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"A Survey on Backdoor Threats in Large Language Models (LLMs): Attacks, Defenses, and Evaluations","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CR","authors_text":"Qingchuan Zhao, Tao Ni, Wei-Bin Lee, Yihe Zhou","submitted_at":"2025-02-06T04:43:05Z","abstract_excerpt":"Large Language Models (LLMs) have achieved significantly advanced capabilities in understanding and generating human language text, which have gained increasing popularity over recent years. Apart from their state-of-the-art natural language processing (NLP) performance, considering their widespread usage in many industries, including medicine, finance, education, etc., security concerns over their usage grow simultaneously. In recent years, the evolution of backdoor attacks has progressed with the advancement of defense mechanisms against them and more well-developed features in the LLMs. In "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2502.05224","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/2502.05224/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":"2502.05224","created_at":"2026-07-05T10:11:34.379258+00:00"},{"alias_kind":"arxiv_version","alias_value":"2502.05224v1","created_at":"2026-07-05T10:11:34.379258+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2502.05224","created_at":"2026-07-05T10:11:34.379258+00:00"},{"alias_kind":"pith_short_12","alias_value":"LLM55LWBED6U","created_at":"2026-07-05T10:11:34.379258+00:00"},{"alias_kind":"pith_short_16","alias_value":"LLM55LWBED6USG4C","created_at":"2026-07-05T10:11:34.379258+00:00"},{"alias_kind":"pith_short_8","alias_value":"LLM55LWB","created_at":"2026-07-05T10:11:34.379258+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":7,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2606.07963","citing_title":"Shared Latent Structures Enable Unified Backdoor Detection and Mitigation in LLMs","ref_index":1,"is_internal_anchor":false},{"citing_arxiv_id":"2607.01019","citing_title":"Toward a Unified Security and Privacy Framework for AI-Native 6G Networks","ref_index":135,"is_internal_anchor":false},{"citing_arxiv_id":"2606.29239","citing_title":"Breaking the Rounding Trap: Securing LLMs against Quantization-Conditioned Backdoors","ref_index":65,"is_internal_anchor":false},{"citing_arxiv_id":"2510.22628","citing_title":"Sentra-Guard: A Real-Time Multilingual Defense Against Adversarial LLM Prompts","ref_index":31,"is_internal_anchor":false},{"citing_arxiv_id":"2604.21700","citing_title":"Stealthy Backdoor Attacks against LLMs Based on Natural Style Triggers","ref_index":21,"is_internal_anchor":false},{"citing_arxiv_id":"2604.09748","citing_title":"Backdoors in RLVR: Jailbreak Backdoors in LLMs From Verifiable Reward","ref_index":7,"is_internal_anchor":false},{"citing_arxiv_id":"2605.02255","citing_title":"On the Privacy of LLMs: An Ablation Study","ref_index":21,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/LLM55LWBED6USG4C4ELVPZC7EE","json":"https://pith.science/pith/LLM55LWBED6USG4C4ELVPZC7EE.json","graph_json":"https://pith.science/api/pith-number/LLM55LWBED6USG4C4ELVPZC7EE/graph.json","events_json":"https://pith.science/api/pith-number/LLM55LWBED6USG4C4ELVPZC7EE/events.json","paper":"https://pith.science/paper/LLM55LWB"},"agent_actions":{"view_html":"https://pith.science/pith/LLM55LWBED6USG4C4ELVPZC7EE","download_json":"https://pith.science/pith/LLM55LWBED6USG4C4ELVPZC7EE.json","view_paper":"https://pith.science/paper/LLM55LWB","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2502.05224&json=true","fetch_graph":"https://pith.science/api/pith-number/LLM55LWBED6USG4C4ELVPZC7EE/graph.json","fetch_events":"https://pith.science/api/pith-number/LLM55LWBED6USG4C4ELVPZC7EE/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/LLM55LWBED6USG4C4ELVPZC7EE/action/timestamp_anchor","attest_storage":"https://pith.science/pith/LLM55LWBED6USG4C4ELVPZC7EE/action/storage_attestation","attest_author":"https://pith.science/pith/LLM55LWBED6USG4C4ELVPZC7EE/action/author_attestation","sign_citation":"https://pith.science/pith/LLM55LWBED6USG4C4ELVPZC7EE/action/citation_signature","submit_replication":"https://pith.science/pith/LLM55LWBED6USG4C4ELVPZC7EE/action/replication_record"}},"created_at":"2026-07-05T10:11:34.379258+00:00","updated_at":"2026-07-05T10:11:34.379258+00:00"}