Do not write that jailbreak paper

Javier RandoICLR 2025 · OpenReview

Abstract

Jailbreaks are becoming a new ImageNet competition instead of helping us better understand LLM security. This blogpost surveys the jailbreak literature to extract the most important contributions and encourages the community to revisit their choices and focus on research that can uncover new security vulnerabilities.
BibTeX
@inproceedings{rando2025do,
  author = {Javier Rando},
  title = {{Do not write that jailbreak paper}},
  booktitle = {International Conference on Learning Representations},
  year = {2025},
  url = {https://openreview.net/forum?id=TbN25IjHyC},
}

Loading related content...

Figure