Network intrusion detection model based on neural network feature extraction and PSO-SVM

Network intrusion detection system plays an important role in network security. Aiming at the problem that it is difficult to extract subtle intrusion features in the process of intrusion detection, a network intrusion detection model based on neural network feature extraction and particle swarm optimization algorithm to optimize support vector machine is proposed. In this method, the one-dimensional network data is constructed into two-dimensional matrix data, which is used as the input of convolutional neural network, and the feature information is extracted from the full connection layer. Finally, the accuracy of intrusion detection is improved by the optimized classifier. In order to verify the detection performance of this method, this model is compared with two-dimensional convolutional neural network and particle swarm optimization algorithm to optimize support vector machine. The experimental results show that the model can not only improve the accuracy of intrusion detection, but also perform well in small sample detection.