Big Data Framework to Detect and Mitigate Distributed Denial of Service(DDoS) Attacks in Software-Defined Networks (SDN)

The software-defined network is in recent years come into the sight of so many network designers as a successor to the traditional network. This type of network is vulnerable to DDoS attacks, targeting a different part of the SDN network architecture by continuously injecting fake flows. It imposes substantial processing on the controller, and the result ultimately leads to the inaccessibility of the controller and the lack of network service to legitimate users.This paper proposes a scalable and reliable real-time DDoS attack detection and mitigation framework using machine learning incorporated with a big data pipeline infrastructure for the SDN environment. The framework supports the detection of DDoS attacks with the ability of processing and analyzing the huge amount of network traffic in near real-time. The framework employs the power of big data solutions, such as Apache Kafka, and Apache Spark in order to realize a scalable pipeline for big data processing.The main objective of this research is to offer a vital supporter which can assist network security systems in addressing the DDoS threats in the SDN environment. For this purpose, machine learning algorithms are also utilized to provide a viable opportunity for classifying network data and detecting DDoS attacks in this regard.