@article{autodanautomaticandinterpretable,
  title = {AutoDAN: Interpretable Gradient-Based Adversarial Attacks on Large Language Models},
  author = {Sicheng Zhu and Ruiyi Zhang and Bang An and Gang Wu and Joe Barrow and Zichao Wang and Furong Huang and Ani Nenkova and Tong Sun},
  year = {2023},
  eprint = {2310.15140},
  archivePrefix = {arXiv},
  url = {https://arxiv.org/abs/2310.15140v2},
}