Investigation of Fuzzy Adaptive Resonance Theory in Network Anomaly Intrusion Detection

Authors:
Nawa Ngamwitthayanon;Naruemon Wattanapongsakorn;David W. Coit
Affiliations:
Department of Computer Engineering, King Mongkut's University of Technology Thonburi, Bangkok, Thailand 10140;Department of Computer Engineering, King Mongkut's University of Technology Thonburi, Bangkok, Thailand 10140;Department of Industrial and Systems Engineering, Rutgers University, Piscataway, USA NJ 0885
Venue:
ISNN 2009 Proceedings of the 6th International Symposium on Neural Networks: Advances in Neural Networks - Part II
Year:
2009

Citing 5
Cited 1

Fuzzy ART: Fast stable learning and categorization of analog patterns by an adaptive resonance system

Neural Networks
Adaptive anomaly detection with evolving connectionist systems

Journal of Network and Computer Applications - Special issue: Network and information security: A computational intelligence approach
An overview of anomaly detection techniques: Existing solutions and latest technological trends

Computer Networks: The International Journal of Computer and Telecommunications Networking
A Novel Method for Unsupervised Anomaly Detection Using Unlabelled Data

ICCSA '08 Proceedings of the 2008 International Conference on Computational Sciences and Its Applications
Survey of clustering algorithms

IEEE Transactions on Neural Networks

Practical real-time intrusion detection using machine learning approaches

Computer Communications

Quantified Score

Hi-index	0.00

Visualization

Abstract

The effectiveness of Fuzzy-Adaptive Resonance Theory (Fuzzy-ART or F-ART) is investigated for a Network Anomaly Intrusion Detection (NAID) application. F-ART is able to group similar data instances into clusters. Furthermore, F-ART is an online clustering algorithm that can learn and update its knowledge based on the presence of new instances to the existing clusters. We investigate a one shot fast learning option of F-ART on the network anomaly detection based on KDD CUP '99 evaluation data set and found its effectiveness and robustness to such problems along with the fast response capability that can be applied to provide a real-time detection system.