Malicious packet detection application for SDN by using classifier

Abstract

Software Defined Network (SDN) has provided completely new vista in the field of networking by introducing new features and providing more benefits. SDN consists of two planes, Control Plane and Data Plane (divided from each other). Open Flow (OF) enables the SDN Controller to directly interact with the forwarding plane of network devices such as switches and routers. In this project, we are designing a malacious packet detection application for Software defined network, which will analyze the incoming traffic and alert the administration. Our classifier will detect any malicious virus or activity, based on its training with ISCX dataset (which contains millions of malicious packets). The purpose of using machine learning classifier is that we will achieve a very high error detection accuracy (i.e. above 90%). The project will helps firms in monitoring the incoming packets and will notify instantaneously of any malicious activity that might be taking place.