paperAugust 2025Unreviewed

BlindGuard: Safeguarding LLM-based Multi-Agent Systems under Unknown Attacks

Rui Miao, Yixin Liu, Yili Wang, Xu Shen, Yue Tan, Yiwei Dai, Shirui Pan, Xin Wang

Volume 1

Abstract

The security of LLM-based multi-agent systems (MAS) is critically threatened by propagation vulnerability, where malicious agents can distort collective decision-making through inter-agent message interactions. While existing supervised defense methods demonstrate promising performance, they may be impractical in real-world scenarios due to their heavy reliance on labeled malicious agents to train a supervised malicious detection model. To enable practical and generalizable MAS defenses, in this

Cite

@article{miao2025blindguard,
  title = {{BlindGuard: Safeguarding LLM-based Multi-Agent Systems under Unknown Attacks}},
  author = {Rui Miao and Yixin Liu and Yili Wang and Xu Shen and Yue Tan and Yiwei Dai and Shirui Pan and Xin Wang},
  year = {2025},
  month = aug,
  journal = {Volume 1},
  eprint = {2508.08127},
  archivePrefix = {arXiv},
  doi = {10.48550/arXiv.2508.08127},
  url = {https://www.semanticscholar.org/paper/f583a040e8324257a993935122c7f1e274bdb20a}
}