Masquerade Attack Detection Through Observation Planning for Multi-Robot Systems

摘要

The increasing adoption of autonomous mobile robots comes with a rising concern over the security of these systems. In this work, we examine the dangers that an adversary could pose in a multi-agent robot system. We show that conventional multi-agent plans are vulnerable to strong attackers masquerading as a properly functioning agent. We propose a novel technique to incorporate attack detection into the multi-agent path-finding problem through the simultaneous synthesis of observation plans. We show that by specially crafting the multi-agent plan, the induced inter-agent observations can provide introspective monitoring guarantees; we achieve guarantees that any adversarial agent that plans to break the system-wide security specification must necessarily violate the induced observation plan.