JailbreakOPT: Tool-Assisted Iterative Jailbreak Prompt Optimization

Abstract

Jailbreak attacks expose persistent safety weaknesses in large language models (LLMs), but existing stateless single-turn methods face a trade-off: hand-crafted prompts are expressive but static, while iterative prompt optimization can adapt but often relies on low-level mutations that require many target queries. We propose JailbreakOPT, a tool-assisted framework for improving iterative single-turn jailbreak prompt optimization. JailbreakOPT organizes diverse atomic jailbreak prompts into an at

Categories

Framework mappings

Suggested from the entry's categories.

@misc{shi2026jailbreakopt,
  title = {{JailbreakOPT: Tool-Assisted Iterative Jailbreak Prompt Optimization}},
  author = {Ge Shi and Jun Yin and Donglin Xie and Fangyi Liu and Yucan Li and Menglin Liu},
  year = {2026},
  month = jun,
  eprint = {2606.11425},
  archivePrefix = {arXiv},
  url = {https://arxiv.org/abs/2606.11425}
}