A network attack path prediction method using attack graph

Abstract

The prediction of intrusion intention of abnormal information in wireless network can effectively guarantee the security and stability of network. Traditional methods describe the relationship between different types of attacks. When building the model, only the path of the network nodes involved in the current attack behavior is considered, so the vulnerability of the network can not be analyzed in detail. Then, a network attack node path detection model based on attack graph is proposed. Firstly, according to the theory of attack graph, the network attack graph is defined, the right state of attacker is detected, the connection matrix of network is obtained, and the formal description of vulnerability, attack effect and attack premise is obtained. Then, the attack path graph is used to describe the transfer relationship between nodes, map the process of the attack from one host or vulnerability to the next host or vulnerability, and give the shortest path to achieve the attack intention. Further obtain the maximum possibility of intrusion under each attack path of the network, and build a network attack node path detection model based on the detection results. The experimental results show that the proposed model has high accuracy and effectively improves the efficiency of network security analysis.