The network intrusion detection system is used to detect and analyze the network traffic and all possible network threats that may affect the system. When the threats are identified the network intrusion detection system immediately takes action such as alerting the administrator or blocking the source of ip address from accessing the network. Various research activities are already conducted to find a efficient and effective solution to prevent intrusions in the network in order to ensure the network security and privacy .machine learning is the one of the efficient and effective techniques to detect network intrusion. Due to high traffic flow, the traditional signature based intrusion detection system is inefficient one to detect anomalies the machine learning techniques is the solution for this. In this paper a combination of two machine learning algorithm is proposed to classify any anomalous behavior in the network traffic. The overall efficiency of the proposed method is dignified recall. However using area under the Receiver operating curve (ROC) metric, we find that genetic algorithm is the best among the two algorithm proposed in this work.

Intrusion detection,Genetic Algorithm, Rbf algorithm, Roc metrics calculation

[1] Syarif I, Prugel Bennett A, Wills G., “Unsupervised clustering approach for network anomaly detection”, Networked Digital Technologies Communications in Computer and Information Science, vol. 293. Berlin Heidelberg: Springer, 2012, pp.135–45.
[2] S. Novakov, C.-H. Lung, I. Lambadaris, Ioannis N. Seddigh, “Studies in applying PCA and wavelet algorithms for network traffic anomaly detection”, Proc. of IEEE 14th International Conference on High Performance Switching and Routing, 2013, pp. 185-190.
[3]Intrusion Detection using an Ensemble of Classification Methods, M.Govindarajan and RM.Chandrasekaran, Proceedings of the World Congress on Engineering and Computer Science 2012 Vol I WCECS 2012, October 24-26, 2012, San Francisco, USA
[4] S. Novakov, C.-H. Lung, I. Lambadaris, Ioannis N. Seddigh, “Combining statistical and spectral analysis techniques in network traffic anomaly detection”, Proc. of IEEE Conf. on Next Generation Networks and Services, 2012, pp. 94-101.
[5] S.A. Mulay, P. R. Devale, G.V. Garje, “Intrusion Detection System using Support Vector Machine and Decision Tree”, International Journal of Computer Applications, vol. 3, no. 3, 2010.
[6] J. Cannady, “Artificial neural networks for misuse detection,” in Proceedings of the 1998 National Information Systems Secu- rity Conference, pp. 443–456, Arlington, VA, USA, 1998.
[7] S. Pan, T. Morris, and U. Adhikari, “Developing a hybrid intrusion detection system using data mining for power sys- tems,” IEEE Transactions on Smart Grid, vol. 6, no. 6, pp. 3104–3113, 2015.