An intrusion detection based on Bayesian game theory for UAV network

Abstract

Unmanned aerial vehicles (UAVs) have enormous potential in public, civil and military fields, so the security of UAV networks is attracting increasing people’s attention. The existing schemes to network intrusion detection have two main limitations: a high false alarm rate and computational overhead. In this paper, aiming at the problem of UAV network security, an intrusion detection scheme based on Bayesian game theory is proposed. Bayesian game means that game participants do not have complete information on the profit function of the opponent. In this paper, incomplete information means that the IDS agent is not sure of the type of attacker and the attacker is not sure whether its neighbor node is an IDS agent or not. The simulation and experimental comparison show that the proposed scheme achieves a high detection rate of intrusion. In addition, the communication cost of the network is the lowest.