{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:UZNQKDMTZGDGIMCBDUKVKEBPNQ","short_pith_number":"pith:UZNQKDMT","schema_version":"1.0","canonical_sha256":"a65b050d93c9866430411d1555102f6c0bfd37e3d2664385ec23901727b66f7f","source":{"kind":"arxiv","id":"2510.14207","version":3},"attestation_state":"computed","paper":{"title":"Echoes of Human Malice in Agents: Benchmarking LLMs for Multi-Turn Online Harassment Attacks","license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.AI","authors_text":"Abdulkadir Erol, Gauri Sharma, Mina Sonmez, Munmun De Choudhury, Pinxian Lu, Tanmay Sutar, Trilok Padhi, Ugur Kursuncu","submitted_at":"2025-10-16T01:27:44Z","abstract_excerpt":"Large Language Model (LLM) agents are powering a growing share of interactive web applications, yet remain vulnerable to misuse and harm. Prior jailbreak research has largely focused on single-turn prompts, whereas real harassment often unfolds over multi-turn interactions. In this work, we present the Online Harassment Agentic Benchmark consisting of: (i) a synthetic multi-turn harassment conversation dataset, (ii) a multi-agent (e.g., harasser, victim) simulation informed by repeated game theory, (iii) three jailbreak methods attacking agents across memory, planning, and fine-tuning, and (iv"},"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":"2510.14207","kind":"arxiv","version":3},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","primary_cat":"cs.AI","submitted_at":"2025-10-16T01:27:44Z","cross_cats_sorted":[],"title_canon_sha256":"f38fcef65922647fbc6422e0ad40db2d398f4085db62d7c567689742d7e2341b","abstract_canon_sha256":"e3f01bf9a888910414d39e13835a4145239bb8c84f18bf04156077469ebae957"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-06-30T02:17:10.368980Z","signature_b64":"heKg5JhQeU+bvc8KMqf//fB6r9RZlJXiLAw2gXz77XSMxqy9IpFlc4k0USKu9XOEyNWX1zHDox591HfxvzOSCw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"a65b050d93c9866430411d1555102f6c0bfd37e3d2664385ec23901727b66f7f","last_reissued_at":"2026-06-30T02:17:10.368339Z","signature_status":"signed_v1","first_computed_at":"2026-06-30T02:17:10.368339Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Echoes of Human Malice in Agents: Benchmarking LLMs for Multi-Turn Online Harassment Attacks","license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.AI","authors_text":"Abdulkadir Erol, Gauri Sharma, Mina Sonmez, Munmun De Choudhury, Pinxian Lu, Tanmay Sutar, Trilok Padhi, Ugur Kursuncu","submitted_at":"2025-10-16T01:27:44Z","abstract_excerpt":"Large Language Model (LLM) agents are powering a growing share of interactive web applications, yet remain vulnerable to misuse and harm. Prior jailbreak research has largely focused on single-turn prompts, whereas real harassment often unfolds over multi-turn interactions. In this work, we present the Online Harassment Agentic Benchmark consisting of: (i) a synthetic multi-turn harassment conversation dataset, (ii) a multi-agent (e.g., harasser, victim) simulation informed by repeated game theory, (iii) three jailbreak methods attacking agents across memory, planning, and fine-tuning, and (iv"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2510.14207","kind":"arxiv","version":3},"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/2510.14207/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":"2510.14207","created_at":"2026-06-30T02:17:10.368421+00:00"},{"alias_kind":"arxiv_version","alias_value":"2510.14207v3","created_at":"2026-06-30T02:17:10.368421+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2510.14207","created_at":"2026-06-30T02:17:10.368421+00:00"},{"alias_kind":"pith_short_12","alias_value":"UZNQKDMTZGDG","created_at":"2026-06-30T02:17:10.368421+00:00"},{"alias_kind":"pith_short_16","alias_value":"UZNQKDMTZGDGIMCB","created_at":"2026-06-30T02:17:10.368421+00:00"},{"alias_kind":"pith_short_8","alias_value":"UZNQKDMT","created_at":"2026-06-30T02:17:10.368421+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/UZNQKDMTZGDGIMCBDUKVKEBPNQ","json":"https://pith.science/pith/UZNQKDMTZGDGIMCBDUKVKEBPNQ.json","graph_json":"https://pith.science/api/pith-number/UZNQKDMTZGDGIMCBDUKVKEBPNQ/graph.json","events_json":"https://pith.science/api/pith-number/UZNQKDMTZGDGIMCBDUKVKEBPNQ/events.json","paper":"https://pith.science/paper/UZNQKDMT"},"agent_actions":{"view_html":"https://pith.science/pith/UZNQKDMTZGDGIMCBDUKVKEBPNQ","download_json":"https://pith.science/pith/UZNQKDMTZGDGIMCBDUKVKEBPNQ.json","view_paper":"https://pith.science/paper/UZNQKDMT","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2510.14207&json=true","fetch_graph":"https://pith.science/api/pith-number/UZNQKDMTZGDGIMCBDUKVKEBPNQ/graph.json","fetch_events":"https://pith.science/api/pith-number/UZNQKDMTZGDGIMCBDUKVKEBPNQ/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/UZNQKDMTZGDGIMCBDUKVKEBPNQ/action/timestamp_anchor","attest_storage":"https://pith.science/pith/UZNQKDMTZGDGIMCBDUKVKEBPNQ/action/storage_attestation","attest_author":"https://pith.science/pith/UZNQKDMTZGDGIMCBDUKVKEBPNQ/action/author_attestation","sign_citation":"https://pith.science/pith/UZNQKDMTZGDGIMCBDUKVKEBPNQ/action/citation_signature","submit_replication":"https://pith.science/pith/UZNQKDMTZGDGIMCBDUKVKEBPNQ/action/replication_record"}},"created_at":"2026-06-30T02:17:10.368421+00:00","updated_at":"2026-06-30T02:17:10.368421+00:00"}