DDoS Attack Detection Based on Rényi-RF in SDN Environment

DDoS attacks can be devastating to SDN networks, and how to detect DDoS attacks efficiently and accurately is particularly important. In this paper, a joint detection scheme based on Rényi-RF is proposed for DDoS attacks in SDN environment. Firstly, Rényi entropy is used as the basis for feature extraction. According to the characteristics of DDoS attacks in SDN, five important features for attack monitoring are extracted. Then, Rényi-RF is used to classify and predict network traffic to achieve detection. The experimental results show that the proposed method improves the detection accuracy, precision and recall, shortens the detection time and reduces the false alarm rate compared with other methods.