AutoDAN: Generating Stealthy Jailbreak Prompts on Aligned Large Language Models

@Article{Liu2023AutoDANGS,
 author = {Xiaogeng Liu and Nan Xu and Muhao Chen and Chaowei Xiao},
 booktitle = {International Conference on Learning Representations},
 journal = {ArXiv},
 title = {AutoDAN: Generating Stealthy Jailbreak Prompts on Aligned Large Language Models},
 volume = {abs/2310.04451},
 year = {2023}
}