Tree of Attacks: Jailbreaking Black-Box LLMs with Auto-Generated Subtrees

Abstract

Introduces TAP using an LLM to iteratively refine jailbreak prompts against black-box target models with high success rates.

Categories

Framework mappings

@inproceedings{mehrotra2024tree,
  title = {{Tree of Attacks: Jailbreaking Black-Box LLMs with Auto-Generated Subtrees}},
  author = {Anay Mehrotra and Manolis Zampetakis and Paul Kassianik and Blaine Nelson and Hyrum Anderson and Yaron Singer and Amin Karbasi},
  year = {2024},
  booktitle = {NeurIPS 2024},
  eprint = {2312.02119},
  archivePrefix = {arXiv},
  url = {https://arxiv.org/abs/2312.02119}
}