{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:53JK5GHSVC57PO6OBG47U75N2Q","short_pith_number":"pith:53JK5GHS","schema_version":"1.0","canonical_sha256":"eed2ae98f2a8bbf7bbce09b9fa7fadd40b4fd3668b8fd5895a44004898a7b51d","source":{"kind":"arxiv","id":"2501.00055","version":1},"attestation_state":"computed","paper":{"title":"LLM-Virus: Evolutionary Jailbreak Attack on Large Language Models","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","headline":"","cross_cats":["cs.AI","cs.CL"],"primary_cat":"cs.CR","authors_text":"Junfeng Fang, Kun Wang, Miao Yu, Qingsong Wen, Shirui Pan, Xing Fan, Yingjie Zhou","submitted_at":"2024-12-28T07:48:57Z","abstract_excerpt":"While safety-aligned large language models (LLMs) are increasingly used as the cornerstone for powerful systems such as multi-agent frameworks to solve complex real-world problems, they still suffer from potential adversarial queries, such as jailbreak attacks, which attempt to induce harmful content. Researching attack methods allows us to better understand the limitations of LLM and make trade-offs between helpfulness and safety. However, existing jailbreak attacks are primarily based on opaque optimization techniques (e.g. token-level gradient descent) and heuristic search methods like LLM "},"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":"2501.00055","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.CR","submitted_at":"2024-12-28T07:48:57Z","cross_cats_sorted":["cs.AI","cs.CL"],"title_canon_sha256":"eee3881773689bd97fada5b0219e7178bee9feec34f6ffcbc5c05f1b36a0cac0","abstract_canon_sha256":"5aa7303434e41916d7289c1129f11654ccaed65e25d7c3354cb6a21a64de87b4"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T09:55:38.404440Z","signature_b64":"ObG+D4aLeD2yC7Itomnl48Gid9B1LGKNxxwbAYyKGEmOrhdl410ONRe8UDmcMaAcdaWa08ohHmNfg3j/PQZhAA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"eed2ae98f2a8bbf7bbce09b9fa7fadd40b4fd3668b8fd5895a44004898a7b51d","last_reissued_at":"2026-07-05T09:55:38.403897Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T09:55:38.403897Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"LLM-Virus: Evolutionary Jailbreak Attack on Large Language Models","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","headline":"","cross_cats":["cs.AI","cs.CL"],"primary_cat":"cs.CR","authors_text":"Junfeng Fang, Kun Wang, Miao Yu, Qingsong Wen, Shirui Pan, Xing Fan, Yingjie Zhou","submitted_at":"2024-12-28T07:48:57Z","abstract_excerpt":"While safety-aligned large language models (LLMs) are increasingly used as the cornerstone for powerful systems such as multi-agent frameworks to solve complex real-world problems, they still suffer from potential adversarial queries, such as jailbreak attacks, which attempt to induce harmful content. Researching attack methods allows us to better understand the limitations of LLM and make trade-offs between helpfulness and safety. However, existing jailbreak attacks are primarily based on opaque optimization techniques (e.g. token-level gradient descent) and heuristic search methods like LLM "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2501.00055","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/2501.00055/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":"2501.00055","created_at":"2026-07-05T09:55:38.403958+00:00"},{"alias_kind":"arxiv_version","alias_value":"2501.00055v1","created_at":"2026-07-05T09:55:38.403958+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2501.00055","created_at":"2026-07-05T09:55:38.403958+00:00"},{"alias_kind":"pith_short_12","alias_value":"53JK5GHSVC57","created_at":"2026-07-05T09:55:38.403958+00:00"},{"alias_kind":"pith_short_16","alias_value":"53JK5GHSVC57PO6O","created_at":"2026-07-05T09:55:38.403958+00:00"},{"alias_kind":"pith_short_8","alias_value":"53JK5GHS","created_at":"2026-07-05T09:55:38.403958+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2606.02041","citing_title":"SentGuard: Sentence-Level Streaming Guardrails for Large Language Models","ref_index":23,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/53JK5GHSVC57PO6OBG47U75N2Q","json":"https://pith.science/pith/53JK5GHSVC57PO6OBG47U75N2Q.json","graph_json":"https://pith.science/api/pith-number/53JK5GHSVC57PO6OBG47U75N2Q/graph.json","events_json":"https://pith.science/api/pith-number/53JK5GHSVC57PO6OBG47U75N2Q/events.json","paper":"https://pith.science/paper/53JK5GHS"},"agent_actions":{"view_html":"https://pith.science/pith/53JK5GHSVC57PO6OBG47U75N2Q","download_json":"https://pith.science/pith/53JK5GHSVC57PO6OBG47U75N2Q.json","view_paper":"https://pith.science/paper/53JK5GHS","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2501.00055&json=true","fetch_graph":"https://pith.science/api/pith-number/53JK5GHSVC57PO6OBG47U75N2Q/graph.json","fetch_events":"https://pith.science/api/pith-number/53JK5GHSVC57PO6OBG47U75N2Q/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/53JK5GHSVC57PO6OBG47U75N2Q/action/timestamp_anchor","attest_storage":"https://pith.science/pith/53JK5GHSVC57PO6OBG47U75N2Q/action/storage_attestation","attest_author":"https://pith.science/pith/53JK5GHSVC57PO6OBG47U75N2Q/action/author_attestation","sign_citation":"https://pith.science/pith/53JK5GHSVC57PO6OBG47U75N2Q/action/citation_signature","submit_replication":"https://pith.science/pith/53JK5GHSVC57PO6OBG47U75N2Q/action/replication_record"}},"created_at":"2026-07-05T09:55:38.403958+00:00","updated_at":"2026-07-05T09:55:38.403958+00:00"}