{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,4,13]],"date-time":"2026-04-13T21:43:08Z","timestamp":1776116588708,"version":"3.50.1"},"publisher-location":"New York, NY, USA","reference-count":26,"publisher":"ACM","license":[{"start":{"date-parts":[[2024,8,24]],"date-time":"2024-08-24T00:00:00Z","timestamp":1724457600000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/www.acm.org\/publications\/policies\/copyright_policy#Background"}],"content-domain":{"domain":["dl.acm.org"],"crossmark-restriction":true},"short-container-title":[],"published-print":{"date-parts":[[2024,8,25]]},"DOI":"10.1145\/3637528.3671444","type":"proceedings-article","created":{"date-parts":[[2024,8,25]],"date-time":"2024-08-25T04:55:12Z","timestamp":1724561712000},"page":"6420-6421","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":4,"title":["DARE to Diversify: DAta Driven and Diverse LLM REd Teaming"],"prefix":"10.1145","author":[{"ORCID":"https:\/\/orcid.org\/0000-0001-9245-2546","authenticated-orcid":false,"given":"Manish","family":"Nagireddy","sequence":"first","affiliation":[{"name":"IBM Research, Cambridge, Massachusetts, USA"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-5781-1918","authenticated-orcid":false,"given":"Bernat","family":"Guill\u00e9n Pegueroles","sequence":"additional","affiliation":[{"name":"Google, Zurich, CH"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-8257-9866","authenticated-orcid":false,"given":"Ioana","family":"Baldini","sequence":"additional","affiliation":[{"name":"IBM Research, Yorktown Heights, New York, USA"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"320","published-online":{"date-parts":[[2024,8,24]]},"reference":[{"key":"e_1_3_2_1_1_1","volume-title":"Python Risk Identification Tool for generative AI (PyRIT). \"https:\/\/github.com\/Azure\/PyRIT\" Retrieved","year":"2024","unstructured":". 2024. Python Risk Identification Tool for generative AI (PyRIT). \"https:\/\/github.com\/Azure\/PyRIT\" Retrieved March 27, 2024 from"},{"key":"e_1_3_2_1_2_1","doi-asserted-by":"crossref","unstructured":"Samuel Bowman. 2022. The Dangers of Underclaiming: Reasons for Caution When Reporting How NLP Systems Fail. In ACL.","DOI":"10.18653\/v1\/2022.acl-long.516"},{"key":"e_1_3_2_1_3_1","volume-title":"Explore","author":"Casper Stephen","unstructured":"Stephen Casper, Jason Lin, Joe Kwon, Gatlen Culp, and Dylan Hadfield-Menell. 2023. Explore, Establish, Exploit: Red Teaming Language Models from Scratch. arxiv: 2306.09442"},{"key":"e_1_3_2_1_4_1","volume-title":"Chrysos","author":"Cheng Yixin","year":"2024","unstructured":"Yixin Cheng, Markos Georgopoulos, Volkan Cevher, and Grigorios G. Chrysos. 2024. Leveraging the Context through Multi-Round Interactions for Jailbreaking Attacks. arxiv: 2402.09177 [cs.LG]"},{"key":"e_1_3_2_1_5_1","volume-title":"Tianle Li, Dacheng Li, Hao Zhang, Banghua Zhu, Michael Jordan, Joseph E. Gonzalez, and Ion Stoica.","author":"Chiang Wei-Lin","year":"2024","unstructured":"Wei-Lin Chiang, Lianmin Zheng, Ying Sheng, Anastasios Nikolas Angelopoulos, Tianle Li, Dacheng Li, Hao Zhang, Banghua Zhu, Michael Jordan, Joseph E. Gonzalez, and Ion Stoica. 2024. Chatbot Arena: An Open Platform for Evaluating LLMs by Human Preference. arxiv: 2403.04132 [cs.AI]"},{"key":"e_1_3_2_1_6_1","volume-title":"https:\/\/digital-strategy.ec.europa.eu\/en\/policies\/regulatory-framework-ai Retrieved","author":"European Commission","year":"2024","unstructured":"European Commission. 2023. AI Act. https:\/\/digital-strategy.ec.europa.eu\/en\/policies\/regulatory-framework-ai Retrieved March 27, 2024 from"},{"key":"e_1_3_2_1_7_1","unstructured":"Leon Derczynski Erick Galinkin and Subho Majumdar. 2024. garak: A Framework for Large Language Model Red Teaming. https:\/\/garak.ai."},{"key":"e_1_3_2_1_8_1","volume-title":"Proceedings of the 2022 Conference on Empirical Methods in Natural Language Processing, EMNLP 2022, Abu Dhabi, United Arab Emirates, December 7--11","author":"Ethan","year":"2022","unstructured":"Ethan Perez et al. 2022a. Red Teaming Language Models with Language Models. In Proceedings of the 2022 Conference on Empirical Methods in Natural Language Processing, EMNLP 2022, Abu Dhabi, United Arab Emirates, December 7--11, 2022."},{"key":"e_1_3_2_1_9_1","unstructured":"George Kour et al. 2023a. Unveiling Safety Vulnerabilities of Large Language Models. arxiv: 2311.04124 [cs.CL]"},{"key":"e_1_3_2_1_10_1","volume-title":"Proceedings of the 2022 ACM Conference on Fairness, Accountability, and Transparency.","author":"Laura","unstructured":"Laura Weidinger et al. 2022b. Taxonomy of Risks posed by Language Models. In Proceedings of the 2022 ACM Conference on Fairness, Accountability, and Transparency."},{"key":"e_1_3_2_1_11_1","unstructured":"Laura Weidinger et al. 2023b. Sociotechnical Safety Evaluation of Generative AI Systems. arxiv: 2310.11986"},{"key":"e_1_3_2_1_12_1","unstructured":"Mantas Mazeika et al. 2024a. HarmBench: A Standardized Evaluation Framework for Automated Red Teaming and Robust Refusal. arxiv: 2402.04249 [cs.LG]"},{"key":"e_1_3_2_1_13_1","unstructured":"Zhang-Wei Hong et al. 2024b. Curiosity-driven Red-teaming for Large Language Models."},{"key":"e_1_3_2_1_14_1","volume-title":"Blueprint for an AI Bill of Rights. https:\/\/www.whitehouse.gov\/ostp\/ai-bill-of-rights\/ Retrieved","author":"House White","year":"2024","unstructured":"White House. 2022. Blueprint for an AI Bill of Rights. https:\/\/www.whitehouse.gov\/ostp\/ai-bill-of-rights\/ Retrieved March 27, 2024 from"},{"key":"e_1_3_2_1_15_1","volume-title":"Red-Teaming Large Language Models to Identify Novel AI Risks. https:\/\/www.whitehouse.gov\/ostp\/news-updates\/2023\/08\/29\/red-teaming-large-language-models-to-identify-novel-ai-risks\/ Retrieved","author":"House White","year":"2024","unstructured":"White House. 2023. Red-Teaming Large Language Models to Identify Novel AI Risks. https:\/\/www.whitehouse.gov\/ostp\/news-updates\/2023\/08\/29\/red-teaming-large-language-models-to-identify-novel-ai-risks\/ Retrieved March 27, 2024 from"},{"key":"e_1_3_2_1_16_1","unstructured":"White House. 2024. FACT SHEET: Vice President Harris Announces OMB Policy to Advance Governance Innovation and Risk Management in Federal Agencies Use of Artificial Intelligence. \"https:\/\/www.whitehouse.gov\/briefing-room\/statements-releases\/2024\/03\/28\/fact-sheet-vice-president-harris-announces-omb-policy-to-advance-governance-innovation-and-risk-management-in-federal-agencies-use-of-artificial-intelligence\/\" Retrieved March 28 2024 from"},{"key":"e_1_3_2_1_17_1","volume-title":"AI risk atlas. https:\/\/dataplatform.cloud.ibm.com\/docs\/content\/wsj\/ai-risk-atlas\/ai-risk-atlas.html?context=wx&audience=wdp# Retrieved","author":"IBM.","year":"2024","unstructured":"IBM. 2024. AI risk atlas. https:\/\/dataplatform.cloud.ibm.com\/docs\/content\/wsj\/ai-risk-atlas\/ai-risk-atlas.html?context=wx&audience=wdp# Retrieved March 27, 2024 from"},{"key":"e_1_3_2_1_18_1","volume-title":"GENERATIVE AI RED TEAMING CHALLENGE: TRANSPARENCY REPORT. https:\/\/drive.google.com\/file\/d\/1JqpbIP6DNomkb32umLoiEPombK2-0Rc-\/view.","author":"Intelligence Humane","year":"2024","unstructured":"Humane Intelligence, Seed AI, and DefCon AI Village. 2024. GENERATIVE AI RED TEAMING CHALLENGE: TRANSPARENCY REPORT. https:\/\/drive.google.com\/file\/d\/1JqpbIP6DNomkb32umLoiEPombK2-0Rc-\/view."},{"key":"e_1_3_2_1_19_1","doi-asserted-by":"crossref","unstructured":"Fengqing Jiang Zhangchen Xu Luyao Niu Zhen Xiang Bhaskar Ramasubramanian Bo Li and Radha Poovendran. 2024. ArtPrompt: ASCII Art-based Jailbreak Attacks against Aligned LLMs. In ACL.","DOI":"10.18653\/v1\/2024.acl-long.809"},{"key":"e_1_3_2_1_20_1","volume-title":"AART: AI-Assisted Red-Teaming with Diverse Data Generation for New LLM-powered Applications. In EMNLP: Industry Track, Mingxuan Wang and Imed Zitouni (Eds.).","author":"Radharapu Bhaktipriya","year":"2023","unstructured":"Bhaktipriya Radharapu, Kevin Robinson, Lora Aroyo, and Preethi Lahoti. 2023. AART: AI-Assisted Red-Teaming with Diverse Data Generation for New LLM-powered Applications. In EMNLP: Industry Track, Mingxuan Wang and Imed Zitouni (Eds.)."},{"key":"e_1_3_2_1_21_1","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2023.emnlp-main.302"},{"key":"e_1_3_2_1_22_1","unstructured":"Rusheb Shah Quentin Feuillade-Montixi Soroush Pour Arush Tagade Stephen Casper and Javier Rando. 2023. Scalable and Transferable Black-Box Jailbreaks for Language Models via Persona Modulation. arxiv: 2311.03348 [cs.CL]"},{"key":"e_1_3_2_1_23_1","unstructured":"The Royal Society and Humane Intelligence. 2024. Red teaming large language models (LLMs) for resilience to scientific disinformation."},{"key":"e_1_3_2_1_24_1","volume-title":"Jailbroken: How Does LLM Safety Training Fail?. In Advances in Neural Information Processing Systems.","author":"Wei Alexander","year":"2023","unstructured":"Alexander Wei, Nika Haghtalab, and Jacob Steinhardt. 2023. Jailbroken: How Does LLM Safety Training Fail?. In Advances in Neural Information Processing Systems."},{"key":"e_1_3_2_1_25_1","volume-title":"Pinjia He, Shuming Shi, and Zhaopeng Tu.","author":"Yuan Youliang","year":"2024","unstructured":"Youliang Yuan, Wenxiang Jiao, Wenxuan Wang, Jen tse Huang, Pinjia He, Shuming Shi, and Zhaopeng Tu. 2024. GPT-4 Is Too Smart To Be Safe: Stealthy Chat with LLMs via Cipher. In ICLR."},{"key":"e_1_3_2_1_26_1","doi-asserted-by":"crossref","unstructured":"Yi Zeng Hongpeng Lin Jingwen Zhang Diyi Yang Ruoxi Jia and Weiyan Shi. 2024. How Johnny Can Persuade LLMs to Jailbreak Them: Rethinking Persuasion to Challenge AI Safety by Humanizing LLMs. arxiv: 2401.06373 [cs.CL]","DOI":"10.18653\/v1\/2024.acl-long.773"}],"event":{"name":"KDD '24: The 30th ACM SIGKDD Conference on Knowledge Discovery and Data Mining","location":"Barcelona Spain","acronym":"KDD '24","sponsor":["SIGMOD ACM Special Interest Group on Management of Data","SIGKDD ACM Special Interest Group on Knowledge Discovery in Data"]},"container-title":["Proceedings of the 30th ACM SIGKDD Conference on Knowledge Discovery and Data Mining"],"original-title":[],"link":[{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3637528.3671444","content-type":"unspecified","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/3637528.3671444","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,6,19]],"date-time":"2025-06-19T00:03:25Z","timestamp":1750291405000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3637528.3671444"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,8,24]]},"references-count":26,"alternative-id":["10.1145\/3637528.3671444","10.1145\/3637528"],"URL":"https:\/\/doi.org\/10.1145\/3637528.3671444","relation":{},"subject":[],"published":{"date-parts":[[2024,8,24]]},"assertion":[{"value":"2024-08-24","order":3,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}]}}