Wireless Network Attack Defense Algorithm Using Deep Neural Network in Internet of Things Environment

Abstract

Aiming at the nonlinearity and uncertainty of the information security threat risk assessment system in the IoT environment, a wireless network attack defense method using deep neural network combined with game model is designed. Firstly, according to the topology information of the network, the reachability relationship and the vulnerability information of the network, the method generates the state attack and defense map of the network. Based on the state attack and defense map, based on the non-cooperative non-zero-sum game model, an optimal attack and defense decision algorithm is proposed. Combined with the prevention and control measures of the vulnerable points, the optimal attack and defense model is generated. Then, the information security risk factor index is quantified by the fuzzy system, and the output of the fuzzy system is input into the radial basis function (RBF) neural network model. The particle swarm optimization algorithm is used to optimize and train the parameters of the RBF neural network. Finally, an optimized defense model is obtained. The simulation results show that the wireless network attack defense algorithm using deep neural network combined with game model can solve the defects of subjective randomness and fuzzy conclusion of traditional wireless network attack defense methods. The average error is less than 2%, and it is more traditional than Machine learning algorithms have higher fitting accuracy, greater learning ability, and faster convergence.