Title :
SVM ensemble for anomaly detection based on rotation forest
Author :
Lin, Liyu ; Zuo, Ruijuan ; Yang, Shuanqiang ; Zhang, Zhengqiu
Author_Institution :
Fac. of Software, Fujian Normal Univ., Fuzhou, China
Abstract :
Due to the expansion of high-speed Internet access, the need for secure and reliable networks has become more critical. The sophistication of network attacks, as well as their severity, has also increased recently. In this paper, a new intelligent intrusion detection system has been proposed using SVM ensemble. The ensemble was made of two-layer, one is composed by five SVM network decided by winner-take-all, the other is a ensemble network composed of five classifier decided by majority voting. The KDD99 data sets was used to test which achieve a better performance.
Keywords :
computer network reliability; computer network security; learning (artificial intelligence); pattern classification; security of data; support vector machines; KDD99 data sets; anomaly detection; classifier ensemble method; high-speed Internet access; intelligent intrusion detection system; majority voting; network attacks; network reliability; network security; rotation forest; support vector machines; two-layer SVM ensemble network; winner-take-all; Accuracy; Classification algorithms; Hidden Markov models; Intrusion detection; Kernel; Support vector machines; Training;
Conference_Titel :
Intelligent Control and Information Processing (ICICIP), 2012 Third International Conference on
Conference_Location :
Dalian
Print_ISBN :
978-1-4577-2144-1
DOI :
10.1109/ICICIP.2012.6391455
