A Novel Anomaly Detection Method in Wireless Network Using Multi-level Classifier Ensembles

Anomaly detection is very crucial in an intrusion detection task since it has capability to discover new types of attacks. The major challenges of anomaly detection are how to maximize the accuracy while maintaining low positive rate. In this paper, we propose new approach on anomaly detection using multi-level classifier ensembles. We employ an ensemble learner as a base classifier of ensemble rather than a single classifier algorithm. We run several experiments to choose the best combination of two-level classifier ensemble model. From our experimental result, it is revealed that the performance of our proposed approach yields satisfactory results over classical classifier ensembles and single classifiers.

[1]  J. Friedman.  Special Invited Paper-Additive logistic regression: A statistical view of boosting , 2000 .

[2]  Janez Demsar,et al.  Statistical Comparisons of Classifiers over Multiple Data Sets , 2006, J. Mach. Learn. Res..

[3]  Ailton Akira Shinoda,et al.  A dataset for evaluating intrusion detection systems in IEEE 802.11 wireless networks , 2014, 2014 IEEE Colombian Conference on Communications and Computing (COLCOM).

[4]  Mohak Shah,et al.  Evaluating Learning Algorithms: A Classification Perspective , 2011 .

[5]  Andrew H. Sung,et al.  Intrusion detection using an ensemble of intelligent paradigms , 2005, J. Netw. Comput. Appl..

[6]  Bayu Adhi Tama,et al.  Performance Analysis of Multiple Classifier System in DoS Attack Detection , 2015, WISA.

[7]  Juan José Rodríguez Diez,et al.  Rotation Forest: A New Classifier Ensemble Method , 2006, IEEE Transactions on Pattern Analysis and Machine Intelligence.

[8]  Ali A. Ghorbani,et al.  A detailed analysis of the KDD CUP 99 data set , 2009, 2009 IEEE Symposium on Computational Intelligence for Security and Defense Applications.

[9]  Bayu Adhi Tama,et al.  A Combination of PSO-Based Feature Selection and Tree-Based Classifiers Ensemble for Intrusion Detection Systems , 2015, CSA/CUTE.

[10]  M. Friedman.  A Comparison of Alternative Tests of Significance for the Problem of $m$ Rankings , 1940 .

[11]  Bayu Adhi Tama,et al.  Classifier Ensemble Design with Rotation Forest to Enhance Attack Detection of IDS in Wireless Network , 2016, 2016 11th Asia Joint Conference on Information Security (AsiaJCIS).