Using SVM to Detect DDoS Attack in SDN Network

Abstract

Software Defined Network(SDN) controller has the global view of the network, but it is vulnerable to DDoS attack. This paper proposes a new model to detect DDoS attack in SDN based on SVM . Firstly The model extracts several key features from the packet-in messages and measures the distribution of each feature by using entropy, then uses trained Support Vector Machine(SVM) algorithm to detect the DDoS attack. Experiments shows that this method can detect security events with high efficiency and mitigate the DDoS attack in real-time.