Intelligent Prediction Method for Network Security Situation based on Big Data and Machine Learning

In order to improve the accuracy and effectiveness of network security situation prediction, and to help enterprises protect their own privacy data, a network security situation intelligent prediction method based on big data and machine learning is proposed. By analyzing the architecture of network information security situational awareness, the data source for the initial network security situational awareness data was first determined. Then, the mean interpolation method was utilized to identify invalid network traffic data and network system operation data, taking into account the characteristics of multi-source data to accurately ascertain the network security situation. Furthermore, big data clustering algorithms were applied to group and quantify the data in network security situation reports. With these quantified grouping results serving as input data items, the cuckoo algorithm was employed to enhance the radial basis function (RBF) neural network, ultimately achieving intelligent prediction of the network security situation. The experimental results show that using the design method for network security situation prediction, the highest accuracy of perception results is 96.7%, and the maximum time for predicting different data network security threat warning levels is 62.45[Formula: see text]ms, and the minimum is 53.78[Formula: see text]ms. Therefore, it can be concluded that using the design method can effectively achieve accurate perception of network information security situation, and the accuracy of perception results is less affected by changes in data size. At the same time, based on accurate network security situation prediction, the corresponding threat warning level of predicted data can be quickly determined, which has good practical application effects.