An Intrusion Detection System Based on Polynomial Feature Correlation Analysis

Li, Qingru; Tan, Zhiyuan; Jamdagni, Aruna; Nanda, Priyadarsi; He, Xiangjian; Han, Wei

Abstract

This paper proposes an anomaly-based Intrusion Detection System (IDS), which flags anomalous network traffic with a distance-based classifier. A polynomial approach was designed and applied in this work to extract hidden correlations from traffic related statistics in order to provide distinguishing features for detection. The proposed IDS was evaluated using the well-known KDD Cup 99 data set. Evaluation results show that the proposed system achieved better detection rates on KDD Cup 99 data set in comparison with another two state-of-the-art detection schemes. Moreover, the computational complexity of the system has been analysed in this paper and shows similar to the two state-of-the-art schemes.

Citation

Li, Q., Tan, Z., Jamdagni, A., Nanda, P., He, X., & Han, W. (2017, August). An Intrusion Detection System Based on Polynomial Feature Correlation Analysis. Presented at 2017 IEEE Trustcom/BigDataSE/ICESS

• Presentation Conference Type: Conference Paper (published)
• Conference Name: 2017 IEEE Trustcom/BigDataSE/ICESS
• Start Date: Aug 1, 2017
• End Date: Aug 4, 2017
• Acceptance Date: May 24, 2017
• Online Publication Date: Sep 11, 2017
• Publication Date: Sep 11, 2017
• Deposit Date: Aug 4, 2017
• Publicly Available Date: Aug 7, 2017
• Publisher: Institute of Electrical and Electronics Engineers
• Series ISSN: 2324-9013
• Book Title: 2017 IEEE Trustcom/BigDataSE/I​SPA Conference Proceedings
• Chapter Number: NA
• ISBN: 9781509049066
• DOI: https://doi.org/10.1109/trustcom/bigdatase/icess.2017.340
• Keywords: Intrusion Detection System (IDS), polynomial, feature correlation analysis, Mahalanobis distance, computational complexity
• Public URL: http://researchrepository.napier.ac.uk/Output/946969
• Contract Date: Aug 4, 2017