Denial-of-Service Attack Detection Based on Multivariate Correlation Analysis and triangle map generation
Miss. Kanchan D Sherkar, Sandip A. Kahate · Asian Journal For Convergence In Technology (AJCT) ISSN -2350-1146 · 2015
In the age of information technology the facets of work and availability of everything on internet need is to Interconnected network as well as different systems, such as Web servers, database servers, cloud computing servers, grid computing server etc., are now under threads from network attackers. As one of most common and aggressive means, Denial-ofService (DoS) attacks cause serious impact on these different computing systems. In this paper, we present DoS attack detection and prevention system that uses Multivariate Correlation Analysis (MCA) for accurate network traffic characterization by extracting the geometrical correlations between network traffic features. Our MCA-based DoS attack detection system employs the principle of anomaly-based detection in attack recognition means detection and prevention. This makes our solution capable of detecting known and unknown DoS attacks effectively by learning the patterns of legitimate network traffic only. Furthermore, a triangle-area-based technique is proposed to enhance and to speed up the process of MCA and increases the utilization. The effectiveness of our proposed detection system is evaluated using KDD Cup 99 dataset, and the influences of both non-normalized data and normalized data on the performance of the proposed detection system are examined. The results show that our system outperforms two other previously developed stateof-the-art approaches in terms of detection accuracy.