DDoS detection and filtering technique in cloud environment using GARCH model

In this paper, we present our proposed technique which can detect and filter variety of DDoS attacks in cloud environment. It uses non-linear time series model (i.e. (GARCH) to correctly predict the traffic state as it is able to captures long-range dependence (LRD) and long-tail distribution which is the property of general network traffic. Moreover, Chaos theory is used for the DDoS attack detection. Filtering is done with the help of back propagation artificial neural network (ANN) on the traffic which exceeds the certain limit specified by some threshold. Experimental results show the supremacy of the proposed approach over other approaches.