arXiv cs.AI
· Papers
OpenEvoShield: Dual Non-Stationary Continual Defense for Open-World Multi-Agent System Attacks
arXiv:2607.19351v1 Announce Type: new Abstract: LLM-based multi-agent systems (LLM-MAS) are increasingly deployed in safety-critical applications, where adversaries inject malicious instructions through inter-agent communication to propagate harmful behaviors. Unlike static threats, these attacks are doubly dynamic: ad