{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:DZXF2GWYALRVJMD67AI2M7XJXA","short_pith_number":"pith:DZXF2GWY","schema_version":"1.0","canonical_sha256":"1e6e5d1ad802e354b07ef811a67ee9b80a97f67c3a98a9ebd26118b66f4543bd","source":{"kind":"arxiv","id":"2407.16667","version":1},"attestation_state":"computed","paper":{"title":"RedAgent: Red Teaming Large Language Models with Context-aware Autonomous Language Agent","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.CL"],"primary_cat":"cs.CR","authors_text":"Feng Xiao, Huiyu Xu, Kui Ren, Rui Zheng, Wenhui Zhang, Yunhe Feng, Zhibo Wang, Zhongjie Ba","submitted_at":"2024-07-23T17:34:36Z","abstract_excerpt":"Recently, advanced Large Language Models (LLMs) such as GPT-4 have been integrated into many real-world applications like Code Copilot. These applications have significantly expanded the attack surface of LLMs, exposing them to a variety of threats. Among them, jailbreak attacks that induce toxic responses through jailbreak prompts have raised critical safety concerns. To identify these threats, a growing number of red teaming approaches simulate potential adversarial scenarios by crafting jailbreak prompts to test the target LLM. However, existing red teaming methods do not consider the uniqu"},"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":"2407.16667","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CR","submitted_at":"2024-07-23T17:34:36Z","cross_cats_sorted":["cs.AI","cs.CL"],"title_canon_sha256":"94f19678efe4786aa19ded4ad992484c7e2a9e4599758792bbd0bb51da351b03","abstract_canon_sha256":"d1bcbbb1799bda813236ede67d396a64da7fd03ff37c080b09fe0ace38647dc3"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T08:47:36.735628Z","signature_b64":"8NbJDnldUCsAJplBw2PcI7hlV2+EE1NTSwPZ9kMY3+k4/LpW8oNLmfAekGXR1wXRG/sX5GrhLddpaTD4eUAeDQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"1e6e5d1ad802e354b07ef811a67ee9b80a97f67c3a98a9ebd26118b66f4543bd","last_reissued_at":"2026-07-05T08:47:36.735015Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T08:47:36.735015Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"RedAgent: Red Teaming Large Language Models with Context-aware Autonomous Language Agent","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.CL"],"primary_cat":"cs.CR","authors_text":"Feng Xiao, Huiyu Xu, Kui Ren, Rui Zheng, Wenhui Zhang, Yunhe Feng, Zhibo Wang, Zhongjie Ba","submitted_at":"2024-07-23T17:34:36Z","abstract_excerpt":"Recently, advanced Large Language Models (LLMs) such as GPT-4 have been integrated into many real-world applications like Code Copilot. These applications have significantly expanded the attack surface of LLMs, exposing them to a variety of threats. Among them, jailbreak attacks that induce toxic responses through jailbreak prompts have raised critical safety concerns. To identify these threats, a growing number of red teaming approaches simulate potential adversarial scenarios by crafting jailbreak prompts to test the target LLM. However, existing red teaming methods do not consider the uniqu"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2407.16667","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/2407.16667/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":"2407.16667","created_at":"2026-07-05T08:47:36.735091+00:00"},{"alias_kind":"arxiv_version","alias_value":"2407.16667v1","created_at":"2026-07-05T08:47:36.735091+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2407.16667","created_at":"2026-07-05T08:47:36.735091+00:00"},{"alias_kind":"pith_short_12","alias_value":"DZXF2GWYALRV","created_at":"2026-07-05T08:47:36.735091+00:00"},{"alias_kind":"pith_short_16","alias_value":"DZXF2GWYALRVJMD6","created_at":"2026-07-05T08:47:36.735091+00:00"},{"alias_kind":"pith_short_8","alias_value":"DZXF2GWY","created_at":"2026-07-05T08:47:36.735091+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":8,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2606.25476","citing_title":"A Red Teaming Framework for Large Language Models: A Case Study on Faithfulness Evaluation","ref_index":56,"is_internal_anchor":false},{"citing_arxiv_id":"2606.19887","citing_title":"FinRED: An Expert-Guided Benchmark Generation and Evaluation Framework for Financial LLM Red-Teaming","ref_index":33,"is_internal_anchor":false},{"citing_arxiv_id":"2606.02041","citing_title":"SentGuard: Sentence-Level Streaming Guardrails for Large Language Models","ref_index":29,"is_internal_anchor":false},{"citing_arxiv_id":"2511.12710","citing_title":"Evolve the Method, Not the Prompts: Evolutionary Synthesis of Jailbreak Attacks on LLMs","ref_index":53,"is_internal_anchor":false},{"citing_arxiv_id":"2605.17380","citing_title":"ADR: An Agentic Detection System for Enterprise Agentic AI Security","ref_index":35,"is_internal_anchor":false},{"citing_arxiv_id":"2605.05630","citing_title":"One Turn Too Late: Response-Aware Defense Against Hidden Malicious Intent in Multi-Turn Dialogue","ref_index":35,"is_internal_anchor":false},{"citing_arxiv_id":"2605.11730","citing_title":"Persona-Conditioned Adversarial Prompting: Multi-Identity Red-Teaming for Adversarial Discovery and Mitigation","ref_index":30,"is_internal_anchor":false},{"citing_arxiv_id":"2605.05630","citing_title":"One Turn Too Late: Response-Aware Defense Against Hidden Malicious Intent in Multi-Turn Dialogue","ref_index":35,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/DZXF2GWYALRVJMD67AI2M7XJXA","json":"https://pith.science/pith/DZXF2GWYALRVJMD67AI2M7XJXA.json","graph_json":"https://pith.science/api/pith-number/DZXF2GWYALRVJMD67AI2M7XJXA/graph.json","events_json":"https://pith.science/api/pith-number/DZXF2GWYALRVJMD67AI2M7XJXA/events.json","paper":"https://pith.science/paper/DZXF2GWY"},"agent_actions":{"view_html":"https://pith.science/pith/DZXF2GWYALRVJMD67AI2M7XJXA","download_json":"https://pith.science/pith/DZXF2GWYALRVJMD67AI2M7XJXA.json","view_paper":"https://pith.science/paper/DZXF2GWY","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2407.16667&json=true","fetch_graph":"https://pith.science/api/pith-number/DZXF2GWYALRVJMD67AI2M7XJXA/graph.json","fetch_events":"https://pith.science/api/pith-number/DZXF2GWYALRVJMD67AI2M7XJXA/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/DZXF2GWYALRVJMD67AI2M7XJXA/action/timestamp_anchor","attest_storage":"https://pith.science/pith/DZXF2GWYALRVJMD67AI2M7XJXA/action/storage_attestation","attest_author":"https://pith.science/pith/DZXF2GWYALRVJMD67AI2M7XJXA/action/author_attestation","sign_citation":"https://pith.science/pith/DZXF2GWYALRVJMD67AI2M7XJXA/action/citation_signature","submit_replication":"https://pith.science/pith/DZXF2GWYALRVJMD67AI2M7XJXA/action/replication_record"}},"created_at":"2026-07-05T08:47:36.735091+00:00","updated_at":"2026-07-05T08:47:36.735091+00:00"}