{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:66P4P2ZVSFIGIUHN6X5APTHLUO","short_pith_number":"pith:66P4P2ZV","schema_version":"1.0","canonical_sha256":"f79fc7eb3591506450edf5fa07cceba386a94d741c4733fb45aea0c2272debbb","source":{"kind":"arxiv","id":"2401.16765","version":1},"attestation_state":"computed","paper":{"title":"A Cross-Language Investigation into Jailbreak Attacks in Large Language Models","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CR","authors_text":"ChongYang Liu, Jie Li, Ling Shi, Xiaoning Ren, Yang Liu, Yaowen Zheng, Yi Liu, Yinxing Xue","submitted_at":"2024-01-30T06:04:04Z","abstract_excerpt":"Large Language Models (LLMs) have become increasingly popular for their advanced text generation capabilities across various domains. However, like any software, they face security challenges, including the risk of 'jailbreak' attacks that manipulate LLMs to produce prohibited content. A particularly underexplored area is the Multilingual Jailbreak attack, where malicious questions are translated into various languages to evade safety filters. Currently, there is a lack of comprehensive empirical studies addressing this specific threat.\n  To address this research gap, we conducted an extensive"},"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":"2401.16765","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CR","submitted_at":"2024-01-30T06:04:04Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"ac1e7e3731d9089d3f571bf3ec49bbdcc09e42ecfbc7597f34874de25dfdfe7f","abstract_canon_sha256":"fe76bd9c9b063637fa085fa09fc3d955600bd8a22186cb7169d793520600a7b3"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T07:38:59.777090Z","signature_b64":"ngW57ZJgCqwPOUq3//wjI9gtlNAOx+Dc7XY2f6KOre87Y+iJp8hMCMhBhu5RFBvM8v0OUFSdP5k+7X/PFqV9CQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"f79fc7eb3591506450edf5fa07cceba386a94d741c4733fb45aea0c2272debbb","last_reissued_at":"2026-07-05T07:38:59.776679Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T07:38:59.776679Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"A Cross-Language Investigation into Jailbreak Attacks in Large Language Models","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CR","authors_text":"ChongYang Liu, Jie Li, Ling Shi, Xiaoning Ren, Yang Liu, Yaowen Zheng, Yi Liu, Yinxing Xue","submitted_at":"2024-01-30T06:04:04Z","abstract_excerpt":"Large Language Models (LLMs) have become increasingly popular for their advanced text generation capabilities across various domains. However, like any software, they face security challenges, including the risk of 'jailbreak' attacks that manipulate LLMs to produce prohibited content. A particularly underexplored area is the Multilingual Jailbreak attack, where malicious questions are translated into various languages to evade safety filters. Currently, there is a lack of comprehensive empirical studies addressing this specific threat.\n  To address this research gap, we conducted an extensive"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2401.16765","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/2401.16765/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":"2401.16765","created_at":"2026-07-05T07:38:59.776736+00:00"},{"alias_kind":"arxiv_version","alias_value":"2401.16765v1","created_at":"2026-07-05T07:38:59.776736+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2401.16765","created_at":"2026-07-05T07:38:59.776736+00:00"},{"alias_kind":"pith_short_12","alias_value":"66P4P2ZVSFIG","created_at":"2026-07-05T07:38:59.776736+00:00"},{"alias_kind":"pith_short_16","alias_value":"66P4P2ZVSFIGIUHN","created_at":"2026-07-05T07:38:59.776736+00:00"},{"alias_kind":"pith_short_8","alias_value":"66P4P2ZV","created_at":"2026-07-05T07:38:59.776736+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":8,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2606.11202","citing_title":"One Jailbreak, Many Tongues: Learning Language-Insensitive Intention Representations for Multilingual Jailbreak Detection","ref_index":12,"is_internal_anchor":false},{"citing_arxiv_id":"2606.01322","citing_title":"TukaBench: A Culturally Grounded Jailbreak Benchmark for African Languages","ref_index":22,"is_internal_anchor":false},{"citing_arxiv_id":"2502.05206","citing_title":"Safety at Scale: A Comprehensive Survey of Large Model and Agent Safety","ref_index":74,"is_internal_anchor":false},{"citing_arxiv_id":"2510.22628","citing_title":"Sentra-Guard: A Real-Time Multilingual Defense Against Adversarial LLM Prompts","ref_index":26,"is_internal_anchor":false},{"citing_arxiv_id":"2407.04295","citing_title":"Jailbreak Attacks and Defenses Against Large Language Models: A Survey","ref_index":49,"is_internal_anchor":false},{"citing_arxiv_id":"2604.25716","citing_title":"Cross-Lingual Jailbreak Detection via Semantic Codebooks","ref_index":10,"is_internal_anchor":false},{"citing_arxiv_id":"2605.02971","citing_title":"Multilingual Safety Alignment via Self-Distillation","ref_index":23,"is_internal_anchor":false},{"citing_arxiv_id":"2605.02971","citing_title":"Multilingual Safety Alignment via Self-Distillation","ref_index":23,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/66P4P2ZVSFIGIUHN6X5APTHLUO","json":"https://pith.science/pith/66P4P2ZVSFIGIUHN6X5APTHLUO.json","graph_json":"https://pith.science/api/pith-number/66P4P2ZVSFIGIUHN6X5APTHLUO/graph.json","events_json":"https://pith.science/api/pith-number/66P4P2ZVSFIGIUHN6X5APTHLUO/events.json","paper":"https://pith.science/paper/66P4P2ZV"},"agent_actions":{"view_html":"https://pith.science/pith/66P4P2ZVSFIGIUHN6X5APTHLUO","download_json":"https://pith.science/pith/66P4P2ZVSFIGIUHN6X5APTHLUO.json","view_paper":"https://pith.science/paper/66P4P2ZV","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2401.16765&json=true","fetch_graph":"https://pith.science/api/pith-number/66P4P2ZVSFIGIUHN6X5APTHLUO/graph.json","fetch_events":"https://pith.science/api/pith-number/66P4P2ZVSFIGIUHN6X5APTHLUO/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/66P4P2ZVSFIGIUHN6X5APTHLUO/action/timestamp_anchor","attest_storage":"https://pith.science/pith/66P4P2ZVSFIGIUHN6X5APTHLUO/action/storage_attestation","attest_author":"https://pith.science/pith/66P4P2ZVSFIGIUHN6X5APTHLUO/action/author_attestation","sign_citation":"https://pith.science/pith/66P4P2ZVSFIGIUHN6X5APTHLUO/action/citation_signature","submit_replication":"https://pith.science/pith/66P4P2ZVSFIGIUHN6X5APTHLUO/action/replication_record"}},"created_at":"2026-07-05T07:38:59.776736+00:00","updated_at":"2026-07-05T07:38:59.776736+00:00"}