@article{gradsafedetectingunsafepromptsforllms,
  title = {GradSafe: Detecting Jailbreak Prompts for LLMs via Safety-Critical Gradient Analysis},
  author = {Yueqi Xie and Minghong Fang and Renjie Pi and Neil Gong},
  year = {2024},
  eprint = {2402.13494},
  archivePrefix = {arXiv},
  url = {https://arxiv.org/abs/2402.13494v2},
}