Network Traffic Classification with Flow Based Approach

Traffic classification has a crucial place in today’s technology in terms of detecting events on the network. With the developing encryption and evasion techniques, the toughness of traffic classification is increasing. It is seen that traditional methods have low success rate on current datasets. In this paper, a classification algorithm based on statistical and payload based features with the use of machine learning techniques is proposed. The proposed algorithm has been tested on a dataset containing up-to-date network traffic. The obtained results show that the algorithm has high accuracy.