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

Anay Mehrotra, Manolis Zampetakis, Paul Kassianik, Blaine Nelson, Hyrum Anderson, Yaron Singer, Amin Karbasi

Abstract

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

Categories

Tags

Framework Mappings

Cite This Resource

@article{llmsec202400049,
  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},
  journal = {NeurIPS 2024},
  url = {https://arxiv.org/abs/2312.02119},
}