Network security analysis using big data technology and improved neural network

Abstract

Network security is an important part of the future information world. The degree of social informatization is maturing and network infrastructure is gradually improving, the network has become an indispensable part of human life. With the frequent occurrence of cyber security incidents around the world, cyber security research has become very important. The amount of network data is huge, and it is necessary to use big data (BD) analysis technology and various machine learning algorithms to analyze and predict the network security (NS) situation. In the NS situation awareness technology, the network behavior and the possible impact are mainly identified by analyzing data records. However, existing NS situation awareness models need to be improved, such as large resource overhead, low accuracy of analysis results, low processing efficiency, and inability to apply to real-time and large-scale scenarios. To solve these shortcomings, a new NS BD analysis model is proposed using improved BP neural network. In the model, data is simplified and cleaned according to the characteristics of the data records, thereby solving the problems of heterogeneous data sources and high noise. With the classic BP neural network as the core of the model, the error inverse feedback strategy of the neural network is used to improve the accuracy of the model analysis. The innovation of this article is that when preprocessing the input data, the proposed blocked fuzzy C-means clustering algorithm (BFCM) is used to cluster the features of the data records to strengthen the features of the data, thereby improving the model's precision. First, the structure of the NS awareness model is introduced in detail, and then the relevant steps in the model are described in detail. Finally, a series of experiments have been performed to verify that the proposed model has certain reference value for the perception of NS situations.