Dynamic Detection of Network Attacks Based on Wavelet Neural Network and Hidden Markov Model

With the rapid development of network technology, the problem of network security has become increasingly prominent, and the means of network attack are constantly evolving, which brings great challenges to network security protection. Developing an efficient and accurate network attack detection method is of great significance to ensure network security. This paper aims to explore a dynamic detection method of network attacks based on the combination of wavelet neural network (WNN) and Hidden Markov model (HMM). This paper first introduces the basic principle of WNN and HMM and their application in network attack detection, then explains the construction of WNN, and expounds the use of wavelet decomposition used in the research, and sets up the Identification of Position (IP) detection of network attack. WNN-HMM (Wavelet Transform Neural Network Hidden Markov) model is established. In order to verify the effectiveness of this method, three experiments were designed. By simulating different types of network attacks, the performance of WNN-HM model in detecting network attack behavior pattern is tested. The experimental results show that the model can accurately identify the network attack behavior and has a high detection accuracy. The dynamic detection method of network attack based on WNN and HMM proposed in this paper is an efficient and accurate detection method. This method can not only monitor the network behavior pattern in real time, discover potential network attacks in time, but also accurately evaluate the damage degree of network attacks, and provide powerful technical support for network security protection.