Exploiting Robotic Swarm Characteristics for Adversarial Subversion in Coverage Tasks

Abstract

Multi-robot systems, such as swarms, with large number of members that are homogeneous and anonymous are robust to deletion and addition of members. However, these same properties that make the system robust, create vulnerabilities under certain circumstances. In this work, we study such a case, namely the insertion by adversarial agents, called moles, that subvert the performance of the system. The adversary monitors the swarm's movements during surveillance operations for the presence of holes, i.e. areas that were left uncovered by the swarm. The adversary then adds moles that get positioned in the swarm, in such a way as to deceive the swarms regarding the existence of holes and thus preventing the swarm from discovering and repairing the holes. This problem has significant military applications. Our contributions are as follows: First, to the best of our knowledge, this is the first paper that studies this problem. Second, we provide a formalization of the problem. Third, we provide several algorithms, and characterize them formally and also experimentally. Finally, based on developed theory and algorithms, we present a dynamic scenario and describe adversary control laws to leverage the identified swarm vulnerability.