DoS ATTACK DETECTION SYSTEM BASED ON MULTIVARIATE CORRELATION ANALYSIS

In today’s world the number of online applications are increasing. With the increasing number of online applications the threat to the security of these applications is also increasing. The increasing number of cyber attacks have challenged the security of these online applications. DoS is one such type of cyber-attack which aims at making the website and the resources of the server unavailable to the intended users. In this paper we propose an anomaly based detection for both known and unknown attacks. We propose an MCA based system for accurate traffic characterization by extracting the geometrical correlation between network traffic. We also propose a triangle area based technique which enhances and speedup the MCA process. For evaluating the system KDD Cup 99 dataset is used. KDD Cup 99 dataset has 41 features out of which 10 features with maximum statistical variance are selected.