A Bayes Learning-based Anomaly Detection Approach in Large-scale Networks

Abstract

Abstract. With quick developments of new application patterns and network technologies, network anomalies have an important impact on network operations. How to accurately detect network anomalies has become the hot topic in current communication networks. This paper proposes a new detection approach to diagnose the anomaly in network traffic. Firstly, we use the Bayes learning theory to describe network traffic properties. By the learning process, normal network traffic can correctly be modeled. Secondly, the feature extraction is used to differentiate abnormal network traffic from normal huge traffic. Thirdly, the detail detection algorithm is presented to find the anomalous component in network traffic. Finally, we carry out the detailed simulation experiments. Simulation results indicate that our approach is effective.