Improving Discriminating Accuracy Rate of DDoS Attacks and Flash Events

Abstract

Internet security has become a big issue with the passage of time. Among many threats, the distributed denial-of-service (DDoS) attack is the most frequent threat in the networks. The purpose of the DDoS attacks is to interrupt service availability provided by different web servers. This results in legitimate users not being able to access the servers and hence facing denial of services. On the other hand, flash events are a high amount of legitimate users visiting a website due to a specific event. Consequences of these attacks are more powerful when launched during flash events, which are legitimate traffic and cause a denial of service. The purpose of this study is to build an intelligent network traffic classification model to improve the discrimination accuracy rate of DDoS attacks from flash events traffic. Weka is adopted as the platform for evaluating the performance of a random forest algorithm.