Exploiting Asynchrony in Multi-agent Consensus to Change the Agreement Point

Abstract

Reaching agreement through consensus is fundamental to the operation of distributed systems such as sensor networks, social networks or multi-robot networks. Consensus requires agents in the system to reach an agreement over a variable of interest only through local interactions. In real systems, limitations in resources available to the individual agents and delays in communication typically result in asynchronous discrete time control models for consensus. In this paper, we model the problem where an adversary (or a friend) can exploit asynchrony in updates in a group of agents that use the same control law. By modifying the update frequency of a subset of the agents, the adversary (or friend) can change the final value that the system agrees on.