{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,11,24]],"date-time":"2025-11-24T10:00:11Z","timestamp":1763978411853,"version":"3.28.0"},"reference-count":30,"publisher":"IEEE","license":[{"start":{"date-parts":[[2024,6,30]],"date-time":"2024-06-30T00:00:00Z","timestamp":1719705600000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2024,6,30]],"date-time":"2024-06-30T00:00:00Z","timestamp":1719705600000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2024,6,30]]},"DOI":"10.1109\/ijcnn60899.2024.10650172","type":"proceedings-article","created":{"date-parts":[[2024,9,9]],"date-time":"2024-09-09T17:35:05Z","timestamp":1725903305000},"page":"1-8","source":"Crossref","is-referenced-by-count":1,"title":["CRDA: Content Risk Drift Assessment of Large Language Models through Adversarial Multi-Agent Interaction"],"prefix":"10.1109","author":[{"given":"Zongzhen","family":"Liu","sequence":"first","affiliation":[{"name":"University of Chinese Academy of Sciences,School of Cyberspace Security,Beijing,China"}]},{"given":"Guoyi","family":"Li","sequence":"additional","affiliation":[{"name":"University of Chinese Academy of Sciences,School of Cyberspace Security,Beijing,China"}]},{"given":"Bingkang","family":"Shi","sequence":"additional","affiliation":[{"name":"University of Chinese Academy of Sciences,School of Cyberspace Security,Beijing,China"}]},{"given":"Xiaodan","family":"Zhang","sequence":"additional","affiliation":[{"name":"University of Chinese Academy of Sciences,School of Cyberspace Security,Beijing,China"}]},{"given":"Jingguo","family":"Ge","sequence":"additional","affiliation":[{"name":"University of Chinese Academy of Sciences,School of Cyberspace Security,Beijing,China"}]},{"given":"Yulei","family":"Wu","sequence":"additional","affiliation":[{"name":"University of Bristol,School of Electrical, Electronic and Mechanical Engineering,Bristol,UK"}]},{"given":"Honglei","family":"Lyu","sequence":"additional","affiliation":[{"name":"University of Chinese Academy of Sciences,School of Cyberspace Security,Beijing,China"}]}],"member":"263","reference":[{"volume-title":"Introducing chatgpt","key":"ref1"},{"article-title":"Gpt-4 technical report","year":"2023","author":"Achiam","key":"ref2"},{"key":"ref3","article-title":"Emergent abilities of large language models","author":"Wei","year":"2022","journal-title":"Transactions on Machine Learning Research"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1145\/3586183.3606763"},{"article-title":"Camel: Communicative agents for\u201d mind\" exploration of large language model society","volume-title":"Thirty-seventh Conference on Neural Information Processing Systems","author":"Li","key":"ref5"},{"article-title":"Jailbroken: How does llm safety training fail?","volume-title":"Thirty-seventh Conference on Neural Information Processing Systems","author":"Wei","key":"ref6"},{"article-title":"Recent advances towards safe, responsible, and moral dialogue systems: A survey","year":"2023","author":"Deng","key":"ref7"},{"key":"ref8","first-page":"1877","article-title":"Language models are few-shot learners","volume":"33","author":"Brown","year":"2020","journal-title":"Advances in neural information processing systems"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2020.findings-emnlp.301"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1145\/3461702.3462624"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1162\/99608f92.5317da47"},{"article-title":"Jailbreaking black box large language models in twenty queries","year":"2023","author":"Chao","key":"ref12"},{"article-title":"Safety assessment of chinese large language models","year":"2023","author":"Sun","key":"ref13"},{"article-title":"Red-teaming large language models using chain of utterances for safety-alignment","year":"2023","author":"Bhardwaj","key":"ref14"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.2307\/jj.1640535.12"},{"article-title":"Identifying the risks of lm agents with an lm-emulated sandbox","volume-title":"NeurIPS 2023 Foundation Models for Decision Making Workshop","author":"Ruan","key":"ref16"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2021.sigdial-1.57"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2021.acl-long.416"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2020.emnlp-main.154"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2021.acl-long.329"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2022.emnlp-main.796"},{"article-title":"Exploring ai ethics of chatgpt: A diagnostic analysis","year":"2023","author":"Zhuo","key":"ref22"},{"article-title":"Universal and transferable adversarial attacks on aligned language models","year":"2023","author":"Zou","key":"ref23"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2022.emnlp-main.225"},{"article-title":"R-judge: Benchmarking safety risk awareness for llm agents","year":"2024","author":"Yuan","key":"ref25"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2022.acl-demo.9"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2022.acl-long.26"},{"volume-title":"Baichuan-7b","key":"ref28"},{"volume-title":"Baichuan-13b-chat","key":"ref29"},{"volume-title":"Qwen-7b-chat","key":"ref30"}],"event":{"name":"2024 International Joint Conference on Neural Networks (IJCNN)","start":{"date-parts":[[2024,6,30]]},"location":"Yokohama, Japan","end":{"date-parts":[[2024,7,5]]}},"container-title":["2024 International Joint Conference on Neural Networks (IJCNN)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/10649807\/10649898\/10650172.pdf?arnumber=10650172","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,9,10]],"date-time":"2024-09-10T05:01:50Z","timestamp":1725944510000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10650172\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,6,30]]},"references-count":30,"URL":"https:\/\/doi.org\/10.1109\/ijcnn60899.2024.10650172","relation":{},"subject":[],"published":{"date-parts":[[2024,6,30]]}}}