{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,4,25]],"date-time":"2026-04-25T01:49:27Z","timestamp":1777081767901,"version":"3.51.4"},"publisher-location":"New York, NY, USA","reference-count":9,"publisher":"ACM","license":[{"start":{"date-parts":[[2023,11,26]],"date-time":"2023-11-26T00:00:00Z","timestamp":1700956800000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/www.acm.org\/publications\/policies\/copyright_policy#Background"}],"funder":[{"DOI":"10.13039\/100000001","name":"National Science Foundation","doi-asserted-by":"publisher","award":["CNS-1950171, CNS-2310207"],"award-info":[{"award-number":["CNS-1950171, CNS-2310207"]}],"id":[{"id":"10.13039\/100000001","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":["dl.acm.org"],"crossmark-restriction":true},"short-container-title":[],"published-print":{"date-parts":[[2023,11,26]]},"DOI":"10.1145\/3605760.3623764","type":"proceedings-article","created":{"date-parts":[[2023,11,21]],"date-time":"2023-11-21T23:06:06Z","timestamp":1700607966000},"page":"29-32","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":19,"title":["Jailbreaker in Jail: Moving Target Defense for Large Language Models"],"prefix":"10.1145","author":[{"ORCID":"https:\/\/orcid.org\/0009-0001-0471-7063","authenticated-orcid":false,"given":"Bocheng","family":"Chen","sequence":"first","affiliation":[{"name":"Michigan State University, East Lansing, MI, USA"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0009-0000-3815-0184","authenticated-orcid":false,"given":"Advait","family":"Paliwal","sequence":"additional","affiliation":[{"name":"Michigan State University, East Lansing, MI, USA"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-6272-7668","authenticated-orcid":false,"given":"Qiben","family":"Yan","sequence":"additional","affiliation":[{"name":"Michigan State University, East Lansing, MI, USA"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"320","published-online":{"date-parts":[[2023,11,26]]},"reference":[{"key":"e_1_3_2_1_1_1","unstructured":"Yuntao Bai Andy Jones Kamal Ndousse Amanda Askell Anna Chen Nova DasSarma Dawn Drain Stanislav Fort Deep Ganguli Tom Henighan et al. 2022. Training a helpful and harmless assistant with reinforcement learning from human feedback. arXiv preprint arXiv:2204.05862 (2022)."},{"key":"e_1_3_2_1_2_1","volume-title":"Understanding Multi-Turn Toxic Behaviors in Open-Domain Chatbots. arXiv preprint arXiv:2307.09579","author":"Chen Bocheng","year":"2023","unstructured":"Bocheng Chen, Guangjing Wang, Hanqing Guo, Yuanda Wang, and Qiben Yan. 2023. Understanding Multi-Turn Toxic Behaviors in Open-Domain Chatbots. arXiv preprint arXiv:2307.09579 (2023)."},{"key":"e_1_3_2_1_3_1","doi-asserted-by":"publisher","DOI":"10.1145\/3560828.3564016"},{"key":"e_1_3_2_1_4_1","doi-asserted-by":"publisher","DOI":"10.1145\/3560828.3564010"},{"key":"e_1_3_2_1_5_1","unstructured":"Laiyer.ai. 2023. LLM Guard - The Security Toolkit for LLM Interactions. https:\/\/github.com\/laiyer-ai\/llm-guard.git."},{"key":"e_1_3_2_1_6_1","volume-title":"chat.openai.com\/. Accessed","author":"AI.","year":"2023","unstructured":"OpenAI. 2023. ChatGPT. chat.openai.com\/. Accessed 16 Feb. 2023.."},{"key":"e_1_3_2_1_7_1","first-page":"27730","article-title":"2022. Training language models to follow instructions with human feedback","volume":"35","author":"Ouyang Long","year":"2022","unstructured":"Long Ouyang, Jeffrey Wu, Xu Jiang, Diogo Almeida, Carroll Wainwright, Pamela Mishkin, Chong Zhang, Sandhini Agarwal, Katarina Slama, Alex Ray, et al. 2022. Training language models to follow instructions with human feedback. Advances in Neural Information Processing Systems , Vol. 35 (2022), 27730--27744.","journal-title":"Advances in Neural Information Processing Systems"},{"key":"e_1_3_2_1_8_1","volume-title":"Jailbroken: How Does LLM Safety Training Fail? arXiv preprint arXiv:2307.02483","author":"Wei Alexander","year":"2023","unstructured":"Alexander Wei, Nika Haghtalab, and Jacob Steinhardt. 2023. Jailbroken: How Does LLM Safety Training Fail? arXiv preprint arXiv:2307.02483 (2023)."},{"key":"e_1_3_2_1_9_1","volume-title":"Universal and Transferable Adversarial Attacks on Aligned Language Models. arXiv preprint arXiv:2307.15043","author":"Zou Andy","year":"2023","unstructured":"Andy Zou, Zifan Wang, J Zico Kolter, and Matt Fredrikson. 2023. Universal and Transferable Adversarial Attacks on Aligned Language Models. arXiv preprint arXiv:2307.15043 (2023). io"}],"event":{"name":"CCS '23: ACM SIGSAC Conference on Computer and Communications Security","location":"Copenhagen Denmark","acronym":"CCS '23","sponsor":["SIGSAC ACM Special Interest Group on Security, Audit, and Control"]},"container-title":["Proceedings of the 10th ACM Workshop on Moving Target Defense"],"original-title":[],"link":[{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3605760.3623764","content-type":"unspecified","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/dl.acm.org\/doi\/abs\/10.1145\/3605760.3623764","content-type":"text\/html","content-version":"vor","intended-application":"syndication"},{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/3605760.3623764","content-type":"application\/pdf","content-version":"vor","intended-application":"syndication"},{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/3605760.3623764","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,6,17]],"date-time":"2025-06-17T16:46:11Z","timestamp":1750178771000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3605760.3623764"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2023,11,26]]},"references-count":9,"alternative-id":["10.1145\/3605760.3623764","10.1145\/3605760"],"URL":"https:\/\/doi.org\/10.1145\/3605760.3623764","relation":{},"subject":[],"published":{"date-parts":[[2023,11,26]]},"assertion":[{"value":"2023-11-26","order":3,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}]}}