Abstract
DDoS attacks are the perfect planned attacks with the aim to stop the legitimate users from accessing the system or the service by consuming the bandwidth or by making the system or service unavailable. The attackers do not attack to steal or access any information but they decline the performance of the network and the system. DDoS attack at application layers are difficult to detect because they imitate the legitimate traffic. We used Lyapunav coefficient to check the traffic and patter for being attack traffic or legitimate traffic and a six step technique is designed using chaos theory to secure networks from DDoS attack traffic. In this research article we have proposed a novel approach of detecting DDoS attack using artificial neural network and theory of chaos.