@article{gradientcuffdetectingjailbreakattackson,
  title = {Gradient Cuff: Detecting Jailbreak Attacks on Large Language Models by Exploring Refusal Loss Landscapes},
  author = {Xiaomeng Hu and Pin-Yu Chen and Tsung-Yi Ho},
  year = {2024},
  eprint = {2403.00867},
  archivePrefix = {arXiv},
  url = {https://arxiv.org/abs/2403.00867v3},
}