Network traffic anomaly detection using machine learning approaches

Abstract

One of the biggest challenges for both network administrators and researchers is detecting anomalies in network traffic. If they had a tool that could accurately and expeditiously detect these anomalies, they would prevent many of the serious problems caused by them. We conducted experiments in order to study the relationship between interval-based features of network traffic and several types of network anomalies by using two famous machine learning algorithms: the naıve Bayes and k-nearest neighbor. Our findings will help researchers and network administrators to select effective interval-based features for each particular type of anomaly, and to choose a proper machine learning algorithm for their own network system.