A System for Denial-of-Service Attack Detection Based on Multivariate Correlation Analysis

Zhiyuan Tan, Aruna Jamdagni, Xiangjian He, Priyadarsi Nanda, Ren Ping Liu

IEEE Transactions on Parallel and Distributed Systems · 2013 · 314 citations · 21 references

Concepts

TL;DR

Interconnected systems such as web, database, and cloud servers face growing threats from network attackers, with denial‑of‑service attacks being a common and aggressive means that severely impact these systems. The study introduces a DoS attack detection system that employs multivariate correlation analysis to accurately characterize network traffic by extracting geometrical correlations among traffic features. The MCA‑based system uses anomaly‑based detection, learning legitimate traffic patterns to detect known and unknown DoS attacks, and incorporates a triangle‑area technique to accelerate MCA; its effectiveness was evaluated on the KDD Cup 99 dataset with both normalized and non‑normalized data. The results show that our system outperforms two other previously developed state‑of‑the‑art approaches in terms of detection accuracy.

Abstract

Interconnected systems, such as Web servers, database servers, cloud computing servers and so on, are now under threads from network attackers. As one of most common and aggressive means, denial-of-service (DoS) attacks cause serious impact on these computing systems. In this paper, we present a DoS attack detection 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. 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. The effectiveness of our proposed detection system is evaluated using KDD Cup 99 data set, 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 state-of-the-art approaches in terms of detection accuracy.

References

21