Internet traffic classification using Hidden Naive Bayes model

Internet traffic classification plays an important role for network management. In fact, operators need to better predict future traffic behavior to identify anomalous situations. We present here an approach for traffic classification using Hidden Naive Bayes model and a supervised discretization scheme. This approach can achieve an appropriate performance on a range of application types with accessing only the information that remains unchanged after encryption. At first, we use a supervised method based on idea behind Holte's 1R algorithm for discretization of continuous features derived from packet headers. Then, in order to assign flows to their respective classes, we utilize Hidden Naive Bayes (HNB) model. Finally, we test our scheme using a subset of two data sets and compare it to Tree-Augmented Naive Bayes (TAN) algorithm. Various performance measures namely Accuracy (Auc) and Trust are used for quantitative analysis of our results. Experimental results reveal that our proposed modeling approach based on HNB not only achieves a higher performance in terms of both measures in comparison to TAN algorithm but also learns very well even with a small number of training flows.