An experience report on scalable implementation of DDoS attack detection

Abstract

Distributed Denial of Service (DDoS) attacks are increasingly becoming powerful and crippling many networks and services in Internet. Many methods have been proposed to mitigate and detect DDoS attacks in the literature. These techniques require processing large amount of network traffic in real time. In order to process this bulky network traffic, in this paper we report an experimental investigation of scalable implementation. In our experiments we used distributed computing framework of Apache Hadoop to achieve the scalability. We implemented clustering and classification algorithms for detecting DDoS attack. Several experiments on a DDoS dataset and normal dataset of sizes ranging from 1GB to 80GB resulted in performance improvements. © Springer International Publishing Switzerland 2015.