TECHNOLOGY OPTIMIZING PARAMETERS OF FUZZY ART FOR IMPROVING THE ACCURACY OF NIDS

Intrusion Detection System (IDS) has been developed in order to provide a defense mechanism against the intrusive activities carried over network. This paper discusses an approach of Intrusion detection system using Fuzzy ART technique for clustering with some pre-processing method. From the survey it was found that IDS built using Fuzzy ART has low detection rate and high false alarm rate. Parameters of Fuzzy ART technique such as choice parameter and vigilance parameter have major impact on final outcome. So to overcome the problem of low detection rate and higher false alarm rate we need to optimize these parameters of Fuzzy ART. For optimizing of these parameters external fuzzy controller is used. Experimental results shows the different values of parameters give different detection rates and false alarm rate. And by optimizing the parameters we got reduction in false alarm rate by 2.07%.

[1]  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.

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

[3]  Torsten Kuhlen,et al.  Comparative analysis of fuzzy ART and ART-2A network clustering performance , 1998, IEEE Trans. Neural Networks.

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

[5]  Aurobindo Sundaram,et al.  An introduction to intrusion detection , 1996, CROS.

[6]  Dorothy E. Denning,et al.  An Intrusion-Detection Model , 1987, IEEE Transactions on Software Engineering.

[7]  Krunal Panchal,et al.  Survey of Adaptive Resonance Theory Techniques in IDS , 2014 .

[8]  Hao Song,et al.  A Novel Intrusion Detection Method Based on Adaptive Resonance Theory and Principal Component Analysis , 2009, 2009 WRI International Conference on Communications and Mobile Computing.

[9]  Robert J. Marks,et al.  Fuzzy parameter adaptation in neural systems , 1992, [Proceedings 1992] IJCNN International Joint Conference on Neural Networks.

[10]  Rung-Ching Chen,et al.  Using Fuzzy Neural Networks and rule heuristics for anomaly intrusion detection on database connection , 2008, 2008 International Conference on Machine Learning and Cybernetics.

[11]  Naruemon Wattanapongsakorn,et al.  Fuzzy-ART in network anomaly detection with feature-reduction dataset , 2011, 7th International Conference on Networked Computing.

[12]  H. Ruda,et al.  Adaptive preprocessing for on-line learning with adaptive resonance theory (ART) networks , 1995, Proceedings of 1995 IEEE Workshop on Neural Networks for Signal Processing.

[13]  Peter Mell,et al.  NIST Special Publication on Intrusion Detection Systems , 2001 .

[14]  Xiao Han.  An improved intrusion detection system based on neural network , 2009, 2009 IEEE International Conference on Intelligent Computing and Intelligent Systems.

[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.

[16]  Woraphon Lilakiatsakun,et al.  Intrusion detection technique by using fuzzy ART on computer network security , 2012, 2012 7th IEEE Conference on Industrial Electronics and Applications (ICIEA).

[17]  Abdul Hanan Abdullah,et al.  A Novel Method for Unsupervised Anomaly Detection Using  Unlabelled Data , 2008, 2008 International Conference on Computational Sciences and Its Applications.