Hidden Markov Model Based Real Time Network Security Quantification Method

Abstract

Exactly assessing the security risk of a network is the key to improving the security level of the network. The hidden Markov model based real time network security risk quantification method can get the risk value dynamically and in real-time, whose input is intrusion detection system alerts. The method is better than the traditional static assessment method. The paper resolves main fault of this method, which improves its accuracy and simplifies the configuration by automatically working out matrixes in HMM. In an experimental study we demonstrate the usefulness of our techniques.