Using optimized statistical distances to confront distributed denial of service attacks in software defined networks

Software-defined networks (SDN) are an emerging architecture that provides promising amends to put an end to current infrastructure constraints by optimized bandwidth utilization, flexibility in network management and configuration, and pulling down operating costs in traditional network structures. Despite the advantages of this architecture, SDNs may become the victim of a distributed denial of service (DDOS) attacks as the result of potential vulnerabilities in various layers. Therefore, the rapid detection of attack traffic in the early stages is very important. In this paper, we have proposed statistical solution to detect and to mitigate distributed denial of service attack in software-defined networks utilizing the unique capabilities of the SDN architecture. Here, the exponential weighted moving average protection mechanism (EWMA) in statistical distances is exploited. The simulation results of our extensive experiments showed that our mechanism is able to quick detection of attack traffics and take amendatory actions. Moreover, the evaluations show the superiority of the proposed algorithm with respect to other statistical methods.