In recent years, computer networks have become more and more advanced interms of size, applications, complexity and level of heterogeneity. Moreover,availability and performance are important issues for end users. New types ofcyber-attacks that can affect and damage network performance and availabilityare constantly emerging and some threats, such as Distributed Denial of Service(DDoS) attacks, can be very dangerous and cannot be easily prevented. In thisstudy, we present a novel hybrid approach to detecting a DDoS attack by meansof monitoring abnormal traffic in the network. This approach reads traffic dataand from that it is possible to build a model, by means of which future datamay be predicted and compared with observed data, in order to detect anyabnormal traffic. This approach combines two methods: traffic prediction andchanging detection. To the best of our knowledge, such a combination has neverbeen used in this area before. The approach achieved a highly significantaccuracy rate of 98.3% and sensitivity was 100%, which means that all potentialattacks are detected and prevented from penetrating the network system.
展开▼
