Visible to the public Detection and Mitigation of DDoS Attacks Using Conditional Entropy in Software-defined Networking

TitleDetection and Mitigation of DDoS Attacks Using Conditional Entropy in Software-defined Networking
Publication TypeConference Paper
Year of Publication2019
AuthorsXuanyuan, Ming, Ramsurrun, Visham, Seeam, Amar
Conference Name2019 11th International Conference on Advanced Computing (ICoAC)
Keywordsbasic packet forwarding equipment, centralised control, centralized control, centralized management unit, composability, computer network management, computer network security, conditional entropy, control logic, DDoS, DDoS attack detection, DDoS attack mitigation, DDoS detection, distributed denial of service attacks, Entropy, Human Behavior, lightweight approach, Metrics, mitigation, network resources, network revolution, pubcrawl, Resiliency, SDN, SDN security, software defined networking, software-defined networking, telecommunication control
AbstractSoftware-defined networking (SDN) is a relatively new technology that promotes network revolution. The most distinct characteristic of SDN is the transformation of control logic from the basic packet forwarding equipment to a centralized management unit called controller. However, the centralized control of the network resources is like a double-edged sword, for it not only brings beneficial features but also introduces single point of failure if the controller is under distributed denial of service (DDoS) attacks. In this paper, we introduce a light-weight approach based on conditional entropy to improve the SDN security with an aim of defending DDoS at the early stage. The experimental results show that the proposed method has a high average detection rate of 99.372%.
Citation Keyxuanyuan_detection_2019