Research on Network Behavior Risk Measurement Method Based on Traffic Analysis

Abstract

At present, the network security problem is facing a serious threat, and network security events continue to occur. It has become an important link to prevent network attacks and ensure network security. According to the network security protection measures and security technical requirements, it has become an urgent need to establish appropriate security measurement methods and strengthen the monitoring and analysis of network security status. This study proposes a network behavior risk measurement method based on traffic analysis to accurately and objectively evaluate the security state of the network. Traffic is the most basic behavior of the network and the basis of security risk measurement. Firstly, we regard the traffic data as network behavior to build scenarios. Through differential manifold modeling, the traffic data and topology of the network system are semantically described to form a matrix. Then, after manifold dimensionality reduction, the objective risk assessment value can be obtained by manifold mapping and Riemann metric. In this study, the differential manifold theory is applied to network behavior risk measurement, and the innovation of differential manifold in the field of network behavior risk measurement is given. After giving the network behavior risk measurement theory, we first verify the effectiveness of the proposed method through the simulation experiments. Secondly, the public CIC-IDS-2017 data set is used for analysis and calculation to prove the accuracy of the proposed method.