Detection of DDoS attacks using supervised learning technique

Abstract

The development in digital technologies has been amplified by the drastic growth in the field of digital media applications and it changes the entire life style of the people. The electronic devices and digital contents are becoming more notable and popular among the users. As an emerging research area, security has attracted a lot of attention towards security professionals, experts and practitioners. In spite of this increased interest, this field still faces manifold challenges and issues. Such a fast development in digitization contains a block with attacks from an indirect security attack called Distributed Denial of service. An attack that damages the targets, services or network. The main objective of this paper is to improve the detection rate of the DDoS attacks and to overcome these threats in order to provide a safe network. So, a novel method is proposed in this paper to detect the DDoS attacks using support vector machine. A simulation of a network traffic is created to track and capture the patterns from any type of DDoS attacks with the help of rule creation and blacklisting. Further, using rule creation and SVM model, the simulation result based on different instances of time shows the observations of the real time requests that improves the efficiency of detecting the DDoS attacks.