Detection method of boundary malicious nodes in computer network

Abstract

Computer networks are usually randomly deployed in locations where there is no underlying network infrastructure. When a computer node is exposed to a malicious attack environment, the nodes are vulnerable to unknown attacks, resulting in misplaced errors. Traditional node detection methods are difficult to operate safely without human participation, and the detection speed is slow. In this paper, a method of boundary malicious node detection based on multivariate classification is proposed. First of all, the background and the objectives are described. Then, the detection method is studied. The experimental results show that this method can quickly identify unknown attack problems, and through the effective detection method to complete the detection of boundary malicious nodes, with fast speed and low false detection rate.

Subject Classification:

• MSC2010
• 94C99

Keywords:

• Computer network
• Boundary malicious nodes
• Multivariate classification
• Detection