Using SVM to Detect DDoS Attack in SDN Network

2018 2nd annual International Conference on Cloud Technology and Communication Engineering

计算机科学;无线电电子学

Li, Dong^1 ; Yu, Chang^1 ; Zhou, Qizhao^1 ; Yu, Junqing^1

Network and Computing Center, Huazhong University of Science and Technology, Wuhan, Hubei, China^1

关键词: DDoS Attack;    Global view;    High-efficiency;    Key feature;    Real time;    Security events;    Support vector machine algorithm;   

Others  :  https://iopscience.iop.org/article/10.1088/1757-899X/466/1/012003/pdf
DOI  :  10.1088/1757-899X/466/1/012003

学科分类：计算机科学（综合）

来源: IOP

【 摘 要 】

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.