A Detection Method for Anomaly Flow in Software Defined Network

作者：Peng, Huijun; Sun, Zhe; Zhao, Xuejian; Tan, Shuhua; Sun, Zhixin^*

来源：IEEE Access, 2018, 6: 27809-27817.

DOI：10.1109/ACCESS.2018.2839684

• Intrusion detection
• detection algorithms
• nearest neighbor searches
• SDN

As a new type of network structure, the Software Defined Network (SDN) provides a new solution for networkfiow management and optimization, which has made the accurate detection of anomaly SDNfiows a hot research topic. This paper presents an SDN-basedfiow detection method, builds structures for detecting anomaly SDNfiows and performs classification detection on thefiows using the double P-value of transductive confidence machines for K-nearest neighbors algorithm. The experimental results show that the algorithm proposed achieves a lower false positive rate, higher precision, and better adaptation to the SDN environment than do other algorithms of the same type.

• 出版日期2018
• 单位南京邮电大学