A DDoS attack detection and defense mechanism based on the self-organizing mapping in SDN

Since the emergence of Software Defined Network (SDN), it has been widely concerned by the academia and the industry. However, Distributed Denial of Attack (DDoS) can pose a threat to the SDN. Many papers use machine learning algorithms to detect DDoS attacks in SDN, trying to find a balance between detection accuracy and processing time. The purpose of this paper is to propose a DDoS attack detection and defense mechanism based on the Self-Organizing Mapping (SOM) under SDN environment. The experimental results show that this mechanism can not only maintain the proper precision, but also reduce the processing time. In addition, it can also restore port communication.