Journal of Advanced Computing Systems · 2023 · Journal article

Continual Red-Teaming for In-the-Wild Jailbreaks via Online Guardrail Updates and Guardrail Distillation

Date: 2023-02-09
Citations: 14

Cite

@article{zheng2023continual,
  title = {Continual Red-Teaming for In-the-Wild Jailbreaks via Online Guardrail Updates and Guardrail Distillation},
  author = {Da Zheng and Chen-Yu Li and Harvey Davidson},
  year = {2023},
  journal = {Journal of Advanced Computing Systems},
  doi = {10.69987/jacs.2023.30203},
  url = {https://doi.org/10.69987/jacs.2023.30203},
}