Research On Intrusion Detection Of Wireless Sensor Networks Based On Game Theory

Wide applied of wireless sensor networks extend people's ability to obtain information, but its inherent network characteristics makes it more vulnerable to cyber-attack. As an active security defense technology, intrusion detection system is widely used in wireless sensor networks. Current intrusion detection systems typically have higher detection rates for specific attacks, but powerless for other attacks. Intrusion detection system increases the system's energy consumption while protecting the security of wireless sensor network, thus reduce the lifetime of the network. Study on a resource saving intrusion detection system which can detect a variety of network attack have important theoretical and practical significance.Intrusion detection system based on Game Theory takes game theory as foundation, models the attack-defense process between intrusion detection system and attacker as a non-cooperative game model. Through the analysis of model's equilibrium, demonstrated the necessity of performing intrusion detection system in WSN. To deal with the problem of diversity network intruder attacks, game model has been improved and established a non-cooperative information static game model. By analyzing the model's mixed Nash equilibrium, the optimal defense strategy is obtained. It can balance the detection efficiency and energy consumption of the system. In order to minimize the energy consumption of the system, a prediction algorithm base on auto regressive model is proposed. By predicting the attacker's aggressive behavior to guide the start-up of IDS, effectively reducing the energy consumption of the intrusion detection system.The simulation results show that the intrusion detection system based on game theory not only can resist a variety of network attacks effectively, but also reduce the energy consumption and prolong the lifetime of the network.