An Intrusion Detection Model Based on Multi-scale CNN

Abstract

Intrusion detection is the task of detecting, preventing, and possibly reacting to attacks and intrusions in network-based computer systems. In this paper, an intrusion detection algorithm based on convolutional neural network is proposed. This algorithm adds Batch Normalization algorithm and Inception model to the convolutional neural network to improve the convergence speed of the model and make the model of the training pan. The ability is more powerful, increasing the width and depth of the network, and improving the adaptability of the network to the scale. In this paper, the algorithm is verified by KDD Cup 99 data. Experiments show that the network model has higher accuracy and detection rate than classical BP neural network and SVM algorithm and deep learning algorithm DBN, Improve the classification accuracy of intrusion detection identification.