Optimizing and Tuning RBF Parameters using QPSO Algorithm for Anomaly Detection in Network Intrusion Detection System

Intrusion detection system (IDS) is a kind of security software which inspects all incoming and outgoing network traffic and generates alerts if any attack or unusual behaviour is found in a network. This is helpful in providing security. This paper describes RBF neural network approach for IDS. RBF is a feed forward and supervise technique of neural network. RBF approach has good classification ability but its performance depends on its parameters. Based on survey we find that RBF approach has high false alarm as one of major short comings. To overcome this problem, we need to do optimization and proper tuning of RBF parameters. Optimization of RBF parameters is done by implementing QPSO algorithm and tuning of parameters is done as mentioned in this paper. The proposed algorithm also helps to find which parameter optimizing gives better performance for NIDS. The experimental results of detection rate and false rate is improved which is 99.481% and 0.0169948 respectively. The result of using QPSO algorithm along with RBF is better than conventional RBF.

[1]  Zhifeng Chen,et al.  Application of PSO-RBF Neural Network in Network Intrusion Detection , 2009, 2009 Third International Symposium on Intelligent Information Technology Application.

[2]  Yinfeng Liu.  An improved RBF neural network method for information security evaluation , 2014 .

[3]  Osama S. Faragallah,et al.  Divided two-part adaptive intrusion detection system , 2012, Wireless Networks.

[4]  Haiyang Yu,et al.  Study of Neural Network Technologies in Intrusion Detection Systems , 2009, 2009 5th International Conference on Wireless Communications, Networking and Mobile Computing.

[5]  Bhushan H. Trivedi,et al.  Reducing Features of KDD CUP 1999 Dataset for Anomaly Detection Using Back Propagation Neural Network , 2015, 2015 Fifth International Conference on Advanced Computing & Communication Technologies.

[6]  Bhavin Shah,et al.  Artificial Neural Network based Intrusion Detection System: A Survey , 2012 .

[7]  Bhushan H. Trivedi,et al.  Improving Performance of Mobile Agent Based Intrusion Detection System , 2015, 2015 Fifth International Conference on Advanced Computing & Communication Technologies.

[8]  Fan Zhang,et al.  Network Intrusion Detection Method Based on Radial Basic Function Neural Network , 2009, 2009 International Conference on E-Business and Information System Security.

[9]  Shruti B. Yagnik,et al.  A survey on RBF Neural Network for Intrusion Detection System , 2014 .

[10]  Wang Kun,et al.  A New Training Algorithm for RBF Neural Network Based on PSO and Simulation Study , 2009, 2009 WRI World Congress on Computer Science and Information Engineering.

[11]  Yuan Liu,et al.  Network Anomaly Detection Using RBF Neural Network with Hybrid QPSO , 2008, 2008 IEEE International Conference on Networking, Sensing and Control.

[12]  Wenbo Xu,et al.  Training RBF Neural Network Via Quantum-Behaved Particle Swarm Optimization , 2006, ICONIP.

[13]  Niu Yi,et al.  Research on Intrusion Detection System Based on IRBF , 2012, CIS 2012.

[14]  Kun Zhang,et al.  Intrusion Detection Based on RBF Neural Network , 2009, 2009 International Symposium on Information Engineering and Electronic Commerce.

[15]  D. Lalitha Bhaskari,et al.  Intrusion Detection Using Random Forests Classifier with SMOTE and Feature Reduction , 2013, 2013 International Conference on Cloud & Ubiquitous Computing & Emerging Technologies.