Intrusion Detection Based on Generative Adversarial Network of Reinforcement Learning Strategy for Wireless Sensor Networks

Abstract

Due to the wireless nature of wireless sensor networks (WSN), the network can be deployed in most of the unattended environment, which makes the networks more vulnerable for attackers who may listen to the traffic and inject their own nodes in the sensor network. In our work, we research on a novel machine learning algorithm on intrusion detection based on reinforcement learning (RL) strategy using generative adversarial network (GAN) for WSN which can automatically detect intrusion or malicious attacks into the network. We combine Actor-Critic Algorithm in RL with GAN in a simulated WSN. The GAN is employed as part of RL environment to generate fake data with possible attacks, which is similar to the real data generated by the sensor networks. Its main aim is to confuse the adversarial network into differentiating between the real and fake data with possible attacks. The results that is from the experiments are based on environment of GAN and Network Simulator 3 (NS3) illustrate that Actor-Critic&GAN algorithm enhances security of the simulated WSN by protecting the networks data against adversaries and improves on the accuracy of the detection.