期刊名称：Journal of Theoretical and Applied Information Technology
印刷版ISSN：1992-8645
电子版ISSN：1817-3195
出版年度：2017
卷号：95
期号：8
出版社：Journal of Theoretical and Applied
摘要：Botnets are one of the most threatening cyber-attacks available today. This paper proposes a hybrid system which can effectively detect the presence of C&C, P2P and hybrid botnets in the network. The powerful machine learning algorithms like BayesNet, IBk, KStar, J48 and Random Tree have been deployed for detecting these malwares. The performance and accuracy of the individual classifiers are compared with the ensemble approach. Labelled dataset of botnet logs were collected from the Malware Facility. Secured data was collected from Christ university network and the combined dataset is tested using virtual test bed. The performance of the algorithms is studied in this paper. Ensemble approach out performed individual classifiers.
