A Bifold Software Defined Networking based Defence Mechanism for DDOS Attacks in the Cloud Environment

摘要

Cloud computing is a popular network paradigm, in which security is the major concern. Several security threats are lined up in front of cloud computing technology and is necessary to address the security issues. This work focusses on Distributed Denial of Service (DDoS) attack alone as a partial effort to achieve better security. The main objective of DDoS attack is to halt the server from providing service to the cloud nodes, by triggering much more traffic from different cloud nodes. At this juncture, the server cannot withstand the huge traffic and temporarily stopped. Though these attacks cannot be stopped, it can be detected. For this sake, this paper presents a Bifold SDN based Solution using Genetic algorithm and Covariance matrix (BSSGC). The real time traffic data is collected from the Tshark network analyser tool and the abnormal traffic is distinguished by employing a bifold approach. The initial decision about normal and abnormal attacks is made by genetic algorithm and this decision is refined by forming covariance matrix. The experimental results prove the efficacy of the proposed approach with satisfactory accuracy, sensitivity and specificity rates.