{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:LV2JDKXEFMQFPDYIJ3QRP4MQQZ","short_pith_number":"pith:LV2JDKXE","schema_version":"1.0","canonical_sha256":"5d7491aae42b20578f084ee117f1908651223305dd144eec11c92d90d772544f","source":{"kind":"arxiv","id":"2401.11880","version":3},"attestation_state":"computed","paper":{"title":"PsySafe: A Comprehensive Framework for Psychological-based Attack, Defense, and Evaluation of Multi-agent System Safety","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.CR","cs.MA"],"primary_cat":"cs.CL","authors_text":"Feng Zhao, Hongzhi Gao, Huchuan Lu, Jing Shao, Lijun Li, Lijun Wang, Yongting Zhang, Yu Qiao, Zaibin Zhang","submitted_at":"2024-01-22T12:11:55Z","abstract_excerpt":"Multi-agent systems, when enhanced with Large Language Models (LLMs), exhibit profound capabilities in collective intelligence. However, the potential misuse of this intelligence for malicious purposes presents significant risks. To date, comprehensive research on the safety issues associated with multi-agent systems remains limited. In this paper, we explore these concerns through the innovative lens of agent psychology, revealing that the dark psychological states of agents constitute a significant threat to safety. To tackle these concerns, we propose a comprehensive framework (PsySafe) gro"},"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":"2401.11880","kind":"arxiv","version":3},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2024-01-22T12:11:55Z","cross_cats_sorted":["cs.AI","cs.CR","cs.MA"],"title_canon_sha256":"f2a72b0ccb54ed29b9e3eda50773358fcb4013239ec188694e5d487f305a6e4f","abstract_canon_sha256":"8e244936d465ace47b4506b29f3af3284f9aff132a8323b710571b6798b8ec87"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T08:56:59.221771Z","signature_b64":"MHp4VhLYyOwtLhdsdZmJtBNvsbRbCLjb+vvlbzWjEWBAkZllJzDZs2mL98MKy6mrAMTVh7e5ewc8TXbCLofFDw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"5d7491aae42b20578f084ee117f1908651223305dd144eec11c92d90d772544f","last_reissued_at":"2026-07-05T08:56:59.221345Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T08:56:59.221345Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"PsySafe: A Comprehensive Framework for Psychological-based Attack, Defense, and Evaluation of Multi-agent System Safety","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.CR","cs.MA"],"primary_cat":"cs.CL","authors_text":"Feng Zhao, Hongzhi Gao, Huchuan Lu, Jing Shao, Lijun Li, Lijun Wang, Yongting Zhang, Yu Qiao, Zaibin Zhang","submitted_at":"2024-01-22T12:11:55Z","abstract_excerpt":"Multi-agent systems, when enhanced with Large Language Models (LLMs), exhibit profound capabilities in collective intelligence. However, the potential misuse of this intelligence for malicious purposes presents significant risks. To date, comprehensive research on the safety issues associated with multi-agent systems remains limited. In this paper, we explore these concerns through the innovative lens of agent psychology, revealing that the dark psychological states of agents constitute a significant threat to safety. To tackle these concerns, we propose a comprehensive framework (PsySafe) gro"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2401.11880","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/2401.11880/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":"2401.11880","created_at":"2026-07-05T08:56:59.221404+00:00"},{"alias_kind":"arxiv_version","alias_value":"2401.11880v3","created_at":"2026-07-05T08:56:59.221404+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2401.11880","created_at":"2026-07-05T08:56:59.221404+00:00"},{"alias_kind":"pith_short_12","alias_value":"LV2JDKXEFMQF","created_at":"2026-07-05T08:56:59.221404+00:00"},{"alias_kind":"pith_short_16","alias_value":"LV2JDKXEFMQFPDYI","created_at":"2026-07-05T08:56:59.221404+00:00"},{"alias_kind":"pith_short_8","alias_value":"LV2JDKXE","created_at":"2026-07-05T08:56:59.221404+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":7,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2503.21460","citing_title":"Large Language Model Agent: A Survey on Methodology, Applications and Challenges","ref_index":201,"is_internal_anchor":false},{"citing_arxiv_id":"2605.16282","citing_title":"Taxonomy and Consistency Analysis of Safety Benchmarks for AI Agents","ref_index":67,"is_internal_anchor":false},{"citing_arxiv_id":"2506.02546","citing_title":"To trust or not to trust: Attention-based Trust Management for LLM Multi-Agent Systems","ref_index":49,"is_internal_anchor":false},{"citing_arxiv_id":"2410.07283","citing_title":"Prompt Infection: LLM-to-LLM Prompt Injection within Multi-Agent Systems","ref_index":95,"is_internal_anchor":false},{"citing_arxiv_id":"2410.07283","citing_title":"Prompt Infection: LLM-to-LLM Prompt Injection within Multi-Agent Systems","ref_index":1,"is_internal_anchor":false},{"citing_arxiv_id":"2407.04295","citing_title":"Jailbreak Attacks and Defenses Against Large Language Models: A Survey","ref_index":114,"is_internal_anchor":false},{"citing_arxiv_id":"2605.03242","citing_title":"Enhancing Agent Safety Judgment: Controlled Benchmark Rewriting and Analogical Reasoning for Deceptive Out-of-Distribution Scenarios","ref_index":56,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/LV2JDKXEFMQFPDYIJ3QRP4MQQZ","json":"https://pith.science/pith/LV2JDKXEFMQFPDYIJ3QRP4MQQZ.json","graph_json":"https://pith.science/api/pith-number/LV2JDKXEFMQFPDYIJ3QRP4MQQZ/graph.json","events_json":"https://pith.science/api/pith-number/LV2JDKXEFMQFPDYIJ3QRP4MQQZ/events.json","paper":"https://pith.science/paper/LV2JDKXE"},"agent_actions":{"view_html":"https://pith.science/pith/LV2JDKXEFMQFPDYIJ3QRP4MQQZ","download_json":"https://pith.science/pith/LV2JDKXEFMQFPDYIJ3QRP4MQQZ.json","view_paper":"https://pith.science/paper/LV2JDKXE","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2401.11880&json=true","fetch_graph":"https://pith.science/api/pith-number/LV2JDKXEFMQFPDYIJ3QRP4MQQZ/graph.json","fetch_events":"https://pith.science/api/pith-number/LV2JDKXEFMQFPDYIJ3QRP4MQQZ/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/LV2JDKXEFMQFPDYIJ3QRP4MQQZ/action/timestamp_anchor","attest_storage":"https://pith.science/pith/LV2JDKXEFMQFPDYIJ3QRP4MQQZ/action/storage_attestation","attest_author":"https://pith.science/pith/LV2JDKXEFMQFPDYIJ3QRP4MQQZ/action/author_attestation","sign_citation":"https://pith.science/pith/LV2JDKXEFMQFPDYIJ3QRP4MQQZ/action/citation_signature","submit_replication":"https://pith.science/pith/LV2JDKXEFMQFPDYIJ3QRP4MQQZ/action/replication_record"}},"created_at":"2026-07-05T08:56:59.221404+00:00","updated_at":"2026-07-05T08:56:59.221404+00:00"}