Modeling DDOS attacks in sdn and detection using random forest classifier

Abstract

A Software-defined network paradigm provides flexibility and programmability to deal with the growing users of future networks. As a result of the centralized control attribute, it could be regarded as a single point of failure that is vulner-able to various forms of attacks, such as Distributed denial of service (DDOS) attacks. This study attempts to show a mathematical representation of DDOS attacks in SDN, together with how some five-tuple features contribute to the attacks. The studied features were used to detect DDOS using a random forest classifier. The result shows 96.3% detection accuracy and 96.45% precision.