GPT-4 Is Too Smart To Be Safe: Stealthy Chat with LLMs via Cipher

Youliang Yuan, Wenxiang Jiao, Wenxuan Wang, Jen-tse Huang, Pinjia He, Shuming Shi, Zhaopeng Tu

Abstract

Demonstrates that LLMs can be jailbroken using cipher-based encoding, bypassing safety training designed for natural language.

Categories

Tags

Framework Mappings

Cite This Resource

@article{llmsec202400050,
  title = {GPT-4 Is Too Smart To Be Safe: Stealthy Chat with LLMs via Cipher},
  author = {Youliang Yuan and Wenxiang Jiao and Wenxuan Wang and Jen-tse Huang and Pinjia He and Shuming Shi and Zhaopeng Tu},
  year = {2024},
  journal = {ICLR 2024},
  url = {https://arxiv.org/abs/2308.06463},
}