"Prompter Says": A Linguistic Approach to Understanding and Detecting Jailbreak Attacks Against Large-Language Models

Suggested Citation

Dylan Lee, Shaoyuan Xie, Shagoto Rahman, Kenneth Pat, David Lee and Qi Alfred Chen (2023) “"Prompter Says": A Linguistic Approach to Understanding and Detecting Jailbreak Attacks Against Large-Language Models”, in Proceedings of the 1st ACM Workshop on Large AI Systems and Models with Privacy and Safety Analysis. CCS '24: ACM SIGSAC Conference on Computer and Communications Security, Salt Lake City UT USA: ACM, pp. 77–87. Available at: 10.1145/3689217.3690618.