作者位次 #5/8ACL 2026Poster· Natural Language Processing
B lind G uard: 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
摘要
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 interactions. While existing supervised defense methods demonstrate promising performance, they may be impra...