Efficient DDoS Attack Detection and Prevention Framework Using Two-Level Classification in Cloud Environment

Cloud computing is one of the most important technologies in the IT industry. It has serious security threads such as the Distributed Denial of Service attack. In this kind of attack, the attacker targeted the victim cloud using zombie hosts. This paper proposes a novel framework to detect and prevent these types of attacks using feature extraction and selection methods to reduce the computation time and select optimal features from received packets to help in classification. This classification uses two-level method that is based on fuzzy type-2 logic and support vector machine-neural networks (SVM-NN). CloudSim simulator and KDD CUP dataset of DDoS attack are used to simulate the proposed framework. Finally, this framework shows effective results in terms of detection accuracy and false positive rate.