Multi-step Jailbreaking Privacy Attacks on ChatGPT

Haoran Li, Dadi Guo, Wei Fan, Mingshi Xu, Jie Huang, Fanpu Meng, Yangqiu Song

Abstract

Demonstrates multi-step jailbreaking attacks to extract personal information from ChatGPT, showing how sequential prompting can bypass safety measures.

Categories

Tags

Framework Mappings

Cite This Resource

@article{llmsec202300006,
  title = {Multi-step Jailbreaking Privacy Attacks on ChatGPT},
  author = {Haoran Li and Dadi Guo and Wei Fan and Mingshi Xu and Jie Huang and Fanpu Meng and Yangqiu Song},
  year = {2023},
  journal = {EMNLP 2023 Findings},
  url = {https://arxiv.org/abs/2304.05197},
}