Do Anything Now: Characterizing and Evaluating In-The-Wild Jailbreak Prompts on Large Language Models

Abstract

Collects and analyzes 6,387 jailbreak prompts from the wild, developing a comprehensive taxonomy of jailbreak techniques and evaluating their effectiveness.

Categories

Framework mappings

@inproceedings{shen2023do,
  title = {{Do Anything Now: Characterizing and Evaluating In-The-Wild Jailbreak Prompts on Large Language Models}},
  author = {Xinyue Shen and Zeyuan Chen and Michael Backes and Yun Shen and Yang Zhang},
  year = {2023},
  month = aug,
  booktitle = {CCS 2024},
  eprint = {2308.03825},
  archivePrefix = {arXiv},
  doi = {10.1145/3658644.3670388},
  url = {https://arxiv.org/abs/2308.03825}
}