DATABANK

G-Safeguard: A Topology-Guided Security Lens and Treatment on LLM-based Multi-agent Systems

Shilong Wang, Guibin Zhang, Miao Yu, Guancheng Wan, Fanci Meng, Chongye Guo, Kun Wang, Yang Wang

papercode

prompt injectionadversarial agents

Cite this paper

Credit the original research and its authors.

BibTeX
@misc{wang-2025-g-safeguard-a,
  author = {Shilong Wang and Guibin Zhang and Miao Yu and Guancheng Wan and Fanci Meng and Chongye Guo and Kun Wang and Yang Wang},
  title = {{G-Safeguard: A Topology-Guided Security Lens and Treatment on LLM-based Multi-agent Systems}},
  year = {2025},
  note = {ACL 2025},
  url = {https://arxiv.org/abs/2502.11127}
}