An adaptive KPCA approach for detecting LDoS attack. (2nd June 2015)

• Record Type: Journal Article
• Authors: Zhang, Xiaoyu; Wu, Zhijun; Chen, Jiusheng; Yue, Meng
• Is Part Of: International journal of communication systems. Volume 30:Number 4(2017)
• Page Start: n/a
• Page End: n/a
• Publication Date: 2015-06-02
• Subjects: LDoS -- kernel principal component analysis -- optimal kernel -- anomaly detection; Telecommunication systems -- Periodicals; 621.382
• DOI: 10.1002/dac.2993
• Languages: English
• ISSNs: 1074-5351

Abstract

Summary: Low‐rate denial‐of‐service (LDoS) attack sends out attack packets at low‐average rate of traffic flow in short time. It is stealthier than traditional DoS attack, which makes detection of LDoS extremely difficult. In this paper, an adaptive kernel principal component analysis method is proposed for LDoS attack detection. The network traffic flow is extracted through wavelet multi‐scale analysis. An adaptive kernel principal component analysis method is adopted to detect LDoS attack through the squared prediction error statistics. Key parameters such as the parameter of the radial basis function, the number of principal components, and the squared prediction error confidence limit are adaptively trained with training data and updated with the network environment. Simulation is accomplished in NS‐2 environment, and results prove the favorable LDoS attack detection efficiency by the proposed approach. Copyright © 2015 John Wiley & Sons, Ltd. Abstract : The proposed approach based on adaptive kernel principal component analysis can update the low‐rate denial‐of‐service detection model according to the change of the network environment sampling data. Key parameters such as the parameter of the radial basis function, the number of principal components, and the squared prediction error confidence limit are adaptively trained with data and updated with the network environment.