Estimating Strength of a DDoS Attack in Real Time Using ANN Based Scheme

At present, distributed denial of service attack (DDoS) is most common and harmful threat to Internet infrastructure. Many approaches are given in literature for handling these attacks; however there is no scheme that can completely prevent or detect these attacks. Estimating strength of a DDoS attack in real time is helpful to suppress the effect of a DDoS attack by filtering or rate limiting the most suspicious attack sources. In this paper, we present artificial neural network (ANN) based scheme to estimate strength of a DDoS attack. Datasets generated using NS-2 network simulator running on Linux platform are used for training and testing feed forward neural network. Feed forward neural network with different number of neurons are compared for their estimation performance using mean square error (MSE). Simulation results show proposed scheme can estimate strength of DDoS attack in real time efficiently.