AutoDAN: Generating Stealthy Jailbreak Prompts on Aligned Large Language Models

Xiaogeng Liu, Nan Xu, Muhao Chen, Chaowei Xiao

Abstract

Proposes AutoDAN, a method for automatically generating stealthy jailbreak prompts that are semantically meaningful and can bypass perplexity-based defenses.

Categories

Tags

Framework Mappings

Cite This Resource

@article{llmsec202400048,
  title = {AutoDAN: Generating Stealthy Jailbreak Prompts on Aligned Large Language Models},
  author = {Xiaogeng Liu and Nan Xu and Muhao Chen and Chaowei Xiao},
  year = {2024},
  journal = {ICLR 2024},
  url = {https://arxiv.org/abs/2310.04451},
}