{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:GYVFGTSVMC5CQ527BTVV43DY6U","short_pith_number":"pith:GYVFGTSV","schema_version":"1.0","canonical_sha256":"362a534e5560ba28775f0ceb5e6c78f5025263f12af9d04b32388aca45f87009","source":{"kind":"arxiv","id":"2502.12904","version":2},"attestation_state":"computed","paper":{"title":"Fraud-R1 : A Multi-Round Benchmark for Assessing the Robustness of LLM Against Augmented Fraud and Phishing Inducements","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Derek F. Wong, Di Wang, Junchao Wu, Junchi Yao, Keyu Wang, Lijie Hu, Mengdi Li, Shenzhe Zhu, Shu Yang, Zeyu Wu","submitted_at":"2025-02-18T14:47:02Z","abstract_excerpt":"We introduce Fraud-R1, a benchmark designed to evaluate LLMs' ability to defend against internet fraud and phishing in dynamic, real-world scenarios. Fraud-R1 comprises 8,564 fraud cases sourced from phishing scams, fake job postings, social media, and news, categorized into 5 major fraud types. Unlike previous benchmarks, Fraud-R1 introduces a multi-round evaluation pipeline to assess LLMs' resistance to fraud at different stages, including credibility building, urgency creation, and emotional manipulation. Furthermore, we evaluate 15 LLMs under two settings: 1. Helpful-Assistant, where the L"},"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":"2502.12904","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2025-02-18T14:47:02Z","cross_cats_sorted":[],"title_canon_sha256":"1b40328fb08e9471db2febc593d55a425e9e79eaed615c2e5f92685b8b3b308f","abstract_canon_sha256":"31e6a71ddadac597beddb8114d43b87cfc02de3dc7e1577c62aaa2ae122fdb59"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:09:08.751952Z","signature_b64":"+2u+oRPvuNhHtT7mAEQaZCQA13QsAbNmMqb/QkUMM6vX+b3WLKiZYRDCKOdFxK/gG8nsEAA1lM/2yW9XGKMmBg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"362a534e5560ba28775f0ceb5e6c78f5025263f12af9d04b32388aca45f87009","last_reissued_at":"2026-07-05T11:09:08.751492Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:09:08.751492Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Fraud-R1 : A Multi-Round Benchmark for Assessing the Robustness of LLM Against Augmented Fraud and Phishing Inducements","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Derek F. Wong, Di Wang, Junchao Wu, Junchi Yao, Keyu Wang, Lijie Hu, Mengdi Li, Shenzhe Zhu, Shu Yang, Zeyu Wu","submitted_at":"2025-02-18T14:47:02Z","abstract_excerpt":"We introduce Fraud-R1, a benchmark designed to evaluate LLMs' ability to defend against internet fraud and phishing in dynamic, real-world scenarios. Fraud-R1 comprises 8,564 fraud cases sourced from phishing scams, fake job postings, social media, and news, categorized into 5 major fraud types. Unlike previous benchmarks, Fraud-R1 introduces a multi-round evaluation pipeline to assess LLMs' resistance to fraud at different stages, including credibility building, urgency creation, and emotional manipulation. Furthermore, we evaluate 15 LLMs under two settings: 1. Helpful-Assistant, where the L"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2502.12904","kind":"arxiv","version":2},"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/2502.12904/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":"2502.12904","created_at":"2026-07-05T11:09:08.751547+00:00"},{"alias_kind":"arxiv_version","alias_value":"2502.12904v2","created_at":"2026-07-05T11:09:08.751547+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2502.12904","created_at":"2026-07-05T11:09:08.751547+00:00"},{"alias_kind":"pith_short_12","alias_value":"GYVFGTSVMC5C","created_at":"2026-07-05T11:09:08.751547+00:00"},{"alias_kind":"pith_short_16","alias_value":"GYVFGTSVMC5CQ527","created_at":"2026-07-05T11:09:08.751547+00:00"},{"alias_kind":"pith_short_8","alias_value":"GYVFGTSV","created_at":"2026-07-05T11:09:08.751547+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":2,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2605.20759","citing_title":"Rethinking Fraud Safety Evaluation: Multi-Round Attacks Reveal Safety-Utility Tradeoffs in Graph-Context LLM Defenders","ref_index":13,"is_internal_anchor":false},{"citing_arxiv_id":"2512.13040","citing_title":"Understanding Structured Financial Data with LLMs: A Case Study on Fraud Detection","ref_index":49,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/GYVFGTSVMC5CQ527BTVV43DY6U","json":"https://pith.science/pith/GYVFGTSVMC5CQ527BTVV43DY6U.json","graph_json":"https://pith.science/api/pith-number/GYVFGTSVMC5CQ527BTVV43DY6U/graph.json","events_json":"https://pith.science/api/pith-number/GYVFGTSVMC5CQ527BTVV43DY6U/events.json","paper":"https://pith.science/paper/GYVFGTSV"},"agent_actions":{"view_html":"https://pith.science/pith/GYVFGTSVMC5CQ527BTVV43DY6U","download_json":"https://pith.science/pith/GYVFGTSVMC5CQ527BTVV43DY6U.json","view_paper":"https://pith.science/paper/GYVFGTSV","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2502.12904&json=true","fetch_graph":"https://pith.science/api/pith-number/GYVFGTSVMC5CQ527BTVV43DY6U/graph.json","fetch_events":"https://pith.science/api/pith-number/GYVFGTSVMC5CQ527BTVV43DY6U/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/GYVFGTSVMC5CQ527BTVV43DY6U/action/timestamp_anchor","attest_storage":"https://pith.science/pith/GYVFGTSVMC5CQ527BTVV43DY6U/action/storage_attestation","attest_author":"https://pith.science/pith/GYVFGTSVMC5CQ527BTVV43DY6U/action/author_attestation","sign_citation":"https://pith.science/pith/GYVFGTSVMC5CQ527BTVV43DY6U/action/citation_signature","submit_replication":"https://pith.science/pith/GYVFGTSVMC5CQ527BTVV43DY6U/action/replication_record"}},"created_at":"2026-07-05T11:09:08.751547+00:00","updated_at":"2026-07-05T11:09:08.751547+00:00"}