{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:RJXRC2MWDBLC5D6MDBLQG3QYD7","short_pith_number":"pith:RJXRC2MW","schema_version":"1.0","canonical_sha256":"8a6f11699618562e8fcc1857036e181fd7af617f76c342ae8d42f58633555aa4","source":{"kind":"arxiv","id":"2506.10022","version":1},"attestation_state":"computed","paper":{"title":"LLMs Caught in the Crossfire: Malware Requests and Jailbreak Challenges","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CR","authors_text":"Haoyang Li, Huan Gao, Junyu Gao, Xuelong Li, Zhiyuan Zhao, Zhiyu Lin","submitted_at":"2025-06-09T12:02:39Z","abstract_excerpt":"The widespread adoption of Large Language Models (LLMs) has heightened concerns about their security, particularly their vulnerability to jailbreak attacks that leverage crafted prompts to generate malicious outputs. While prior research has been conducted on general security capabilities of LLMs, their specific susceptibility to jailbreak attacks in code generation remains largely unexplored. To fill this gap, we propose MalwareBench, a benchmark dataset containing 3,520 jailbreaking prompts for malicious code-generation, designed to evaluate LLM robustness against such threats. MalwareBench "},"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":"2506.10022","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CR","submitted_at":"2025-06-09T12:02:39Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"c577cfe0fa8ff191f04540207b2aa8403c6fdd404893ee263a408e65b4c8b8bc","abstract_canon_sha256":"93cb25171fbf38e9d6d024d6e0b642633c9e0034b583ad6a8af1b9aa39bcaebd"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:20:15.342072Z","signature_b64":"8TrAt3SXEDxUmCBEVYMOa5xoYuM0p7vMy1ezPU3Bl5xsbxwtpBQTwRKsgExzGaUmQC7MiXM5tz2QL9g/gYeXAA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"8a6f11699618562e8fcc1857036e181fd7af617f76c342ae8d42f58633555aa4","last_reissued_at":"2026-07-05T11:20:15.341510Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:20:15.341510Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"LLMs Caught in the Crossfire: Malware Requests and Jailbreak Challenges","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CR","authors_text":"Haoyang Li, Huan Gao, Junyu Gao, Xuelong Li, Zhiyuan Zhao, Zhiyu Lin","submitted_at":"2025-06-09T12:02:39Z","abstract_excerpt":"The widespread adoption of Large Language Models (LLMs) has heightened concerns about their security, particularly their vulnerability to jailbreak attacks that leverage crafted prompts to generate malicious outputs. While prior research has been conducted on general security capabilities of LLMs, their specific susceptibility to jailbreak attacks in code generation remains largely unexplored. To fill this gap, we propose MalwareBench, a benchmark dataset containing 3,520 jailbreaking prompts for malicious code-generation, designed to evaluate LLM robustness against such threats. MalwareBench "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2506.10022","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/2506.10022/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":"2506.10022","created_at":"2026-07-05T11:20:15.341574+00:00"},{"alias_kind":"arxiv_version","alias_value":"2506.10022v1","created_at":"2026-07-05T11:20:15.341574+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2506.10022","created_at":"2026-07-05T11:20:15.341574+00:00"},{"alias_kind":"pith_short_12","alias_value":"RJXRC2MWDBLC","created_at":"2026-07-05T11:20:15.341574+00:00"},{"alias_kind":"pith_short_16","alias_value":"RJXRC2MWDBLC5D6M","created_at":"2026-07-05T11:20:15.341574+00:00"},{"alias_kind":"pith_short_8","alias_value":"RJXRC2MW","created_at":"2026-07-05T11:20:15.341574+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":0,"internal_anchor_count":0,"sample":[]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/RJXRC2MWDBLC5D6MDBLQG3QYD7","json":"https://pith.science/pith/RJXRC2MWDBLC5D6MDBLQG3QYD7.json","graph_json":"https://pith.science/api/pith-number/RJXRC2MWDBLC5D6MDBLQG3QYD7/graph.json","events_json":"https://pith.science/api/pith-number/RJXRC2MWDBLC5D6MDBLQG3QYD7/events.json","paper":"https://pith.science/paper/RJXRC2MW"},"agent_actions":{"view_html":"https://pith.science/pith/RJXRC2MWDBLC5D6MDBLQG3QYD7","download_json":"https://pith.science/pith/RJXRC2MWDBLC5D6MDBLQG3QYD7.json","view_paper":"https://pith.science/paper/RJXRC2MW","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2506.10022&json=true","fetch_graph":"https://pith.science/api/pith-number/RJXRC2MWDBLC5D6MDBLQG3QYD7/graph.json","fetch_events":"https://pith.science/api/pith-number/RJXRC2MWDBLC5D6MDBLQG3QYD7/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/RJXRC2MWDBLC5D6MDBLQG3QYD7/action/timestamp_anchor","attest_storage":"https://pith.science/pith/RJXRC2MWDBLC5D6MDBLQG3QYD7/action/storage_attestation","attest_author":"https://pith.science/pith/RJXRC2MWDBLC5D6MDBLQG3QYD7/action/author_attestation","sign_citation":"https://pith.science/pith/RJXRC2MWDBLC5D6MDBLQG3QYD7/action/citation_signature","submit_replication":"https://pith.science/pith/RJXRC2MWDBLC5D6MDBLQG3QYD7/action/replication_record"}},"created_at":"2026-07-05T11:20:15.341574+00:00","updated_at":"2026-07-05T11:20:15.341574+00:00"}