@article{defenseagainstthedarkpromptsmitigating,
  title = {Defense Against the Dark Prompts: Mitigating Best-of-N Jailbreaking with Prompt Evaluation},
  author = {Stuart Armstrong and Matija Franklin and Connor Stevens and Rebecca Gorman},
  year = {2025},
  eprint = {2502.00580},
  archivePrefix = {arXiv},
  url = {https://arxiv.org/abs/2502.00580v1},
}