@article{robustsafetyclassifierforlargelanguage,
  title = {Robust Safety Classifier for Large Language Models: Adversarial Prompt Shield},
  author = {JinHwa Kim and Ali Derakhshan and Ian G. Harris},
  year = {2023},
  eprint = {2311.00172},
  archivePrefix = {arXiv},
  url = {https://arxiv.org/abs/2311.00172v1},
}