Two-Player Incomplete Games of Resilient Multiagent Systems

TL;DR

This paper investigates how multiagent systems under consensus protocols respond to jamming attacks using game theory, showing that incomplete attacker knowledge can prevent successful disruption of consensus.

Contribution

It introduces a game-theoretical framework analyzing incomplete information scenarios in multiagent systems under attack, focusing on Bayesian and perfect Bayesian equilibria.

Findings

Incomplete attacker knowledge can lead to failure in preventing consensus.

Players update beliefs over repeated interactions affecting strategies.

Optimal strategies depend on Bayesian equilibrium analysis.

Abstract

Evolution of agents' dynamics of multiagent systems under consensus protocol in the face of jamming attacks is discussed, where centralized parties are able to influence the control signals of the agents. In this paper we focus on a game-theoretical approach of multiagent systems where the players have incomplete information on their opponents' strength. We consider repeated games with both simultaneous and sequential player actions where players update their beliefs of each other over time. The effect of the players' optimal strategies according to Bayesian Nash Equilibrium and Perfect Bayesian Equilibrium on agents' consensus is examined. It is shown that an attacker with incomplete knowledge may fail to prevent consensus despite having sufficient resources to do so.