2026
Attack the Messages, Not the Agents: A Multi-round Adaptive Stealthy Tampering Framework for LLM-MAS
AAAI 2026technical
Large language model-based multi-agent systems (LLM-MAS) effectively accomplish complex and dynamic tasks through inter-agent communication, but this reliance introduces substantial safety vulnerabilities. Existing attack methods targeting LLM-MAS either compromise agent internals or rely on direct