A multi phased statistical classifier An automated identification of Network traffic applications

Abstract

Network traffic classification is an approach of examining application packets and classifying them into different classes generated from various applications. Network traffic classification indicates an essential role in network security. The traffic Classification technique is a challenging task for a networking atmosphere in which the research community is paying more attention for the last couple of years. Several kinds of research have taken place to classify network traffic based on the statistical features of flow duration, packet inter-arrival time, packet size, etc. Network Traffic Classification is the crucial phase of network monitoring. Once categorized per application, the network traffic can be imposed with appropriate security policies to improve the performance of the network. Application Traffic Identification is an imperative device for sorting out the system as it is the most popular approach to distinguish and characterize the network traffic created from different applications. The conventional classifiers become ineffectual for the newest evolution of network technologies on the Internet. The classification using conventional Port-based and Payload-based techniques has become counterproductive due to inconsistencies. The existing port number-based classifier technique is applicable only for the well-known application because of the ascent of the dynamic porting method. Then payload-based classifier has worked well only for the available data packets that are for non-confidential data packets. And at the same time, monitoring a high-speed internet for analysing the data flow is impractical with the traditional technologies instead, it required multi-hop technologies. Providing multi-hop observers is not an easy and efficient task. newline