GARCH and ANN-based DDoS detection and filtering in cloud computing environment

摘要

Nowadays, distributed denial-of-service (DDoS) attack is one of the major security threats in cloud computing environment as it compromises the availability of the services and risks everything including financial loss, reputation and losing faith of the customers. In this paper, we have proposed a novel solution, which can detect DDoS attack traffic in cloud environment using chaos theory. To predict the network traffic state, nonlinear time series model [i.e., generalised autoregressive conditional heteroskedasticity (GARCH) model] is used as it can capture the long-range dependence (LRD) and long-tail distribution which is an important property of network traffic. Prediction error is calculated using the prediction made by GARCH model and actual traffic pattern. Filtering is carried out using back propagation artificial neural network (ANN) on the traffic that exceeds the certain limit specified by some threshold. In our proposed approach, threshold is calculated dynamically, which makes our approach platform independent.