@misc{wang2023self,
  title={Self-Deception: Reverse Penetrating the Semantic Firewall of Large Language Models},
  author={Zhenhua Wang and Wei Xie and Kai Chen and Baosheng Wang and Zhiwen Gui and Enze Wang},
  year={2023},
  eprint={2308.11521},
  archivePrefix={arXiv},
  primaryClass={cs.CL},
  url={https://arxiv.org/abs/2308.11521}
}