DATABANK

PsySafe: A Comprehensive Framework for Psychological-based Attack, Defense, and Evaluation of Multi-agent System Safety

Zaibin Zhang, Yongting Zhang, Lijun Li, Hongzhi Gao, Lijun Wang, Huchuan Lu, Feng Zhao, Yu Qiao, Jing Shao

papercode

prompt injection

Cite this paper

Credit the original research and its authors.

BibTeX
@misc{zhang-2024-psysafe-a-comprehensive,
  author = {Zaibin Zhang and Yongting Zhang and Lijun Li and Hongzhi Gao and Lijun Wang and Huchuan Lu and Feng Zhao and Yu Qiao and Jing Shao},
  title = {{PsySafe: A Comprehensive Framework for Psychological-based Attack, Defense, and Evaluation of Multi-agent System Safety}},
  year = {2024},
  note = {ACL 2024},
  url = {https://arxiv.org/abs/2401.11880}
}