Optimization of Network Intrusion Detection Model Based on Big Data Analysis

As user usage grows, so do security threats to networks, the Internet, websites, and organizations. Detecting intrusions in such a big data situation is complex. A feature-optimized network intrusion detection model based on extensive data analysis is designed to overcome the limitations of current network intrusion detection models and obtain more ideal results. Firstly, the current modeling status of network intrusion detection is studied, and the influence of features on the results of network intrusion detection is analyzed. Then, the feature optimization mathematical model of network intrusion detection is established. The solution of the feature optimization mathematical model is searched by an adaptive genetic algorithm simulating natural biological evolution. The optimal feature subset of intrusion detection is obtained by back coding the optimal solution. Finally, according to the optimal feature subset, the learning sample of network intrusion detection is modeled, and the optimal network intrusion detection model is designed. Using the standard data set of network intrusion detection for simulation and comparison tests, the average accuracy of this paper’s network intrusion detection model is about 95%, while other current network intrusion detection models are below 95%. Meanwhile, the time of training and the detection of intrusion detection modeling in this model is significantly reduced, and better efficiency of network intrusion detection can be obtained.