The base-rate fallacy and the difficulty of intrusion detection
ACM Transactions on Information and System Security (TISSEC)
Decision tree classifier for network intrusion detection with GA-based feature selection
Proceedings of the 43rd annual Southeast regional conference - Volume 2
Feature selection using rough-DPSO in anomaly intrusion detection
ICCSA'07 Proceedings of the 2007 international conference on Computational science and its applications - Volume Part I
Kernel PCA based network intrusion feature extraction and detection using SVM
ICNC'05 Proceedings of the First international conference on Advances in Natural Computation - Volume Part II
The feature selection and intrusion detection problems
ASIAN'04 Proceedings of the 9th Asian Computing Science conference on Advances in Computer Science: dedicated to Jean-Louis Lassez on the Occasion of His 5th Cycle Birthday
Analysis of three intrusion detection system benchmark datasets using machine learning algorithms
ISI'05 Proceedings of the 2005 IEEE international conference on Intelligence and Security Informatics
Using attack-specific feature subsets for network intrusion detection
AI'06 Proceedings of the 19th Australian joint conference on Artificial Intelligence: advances in Artificial Intelligence
Anomaly detection methods in wired networks: a survey and taxonomy
Computer Communications
Hi-index | 0.00 |
One of a major challenge in IDS is to discover the intrusive patterns which are normally hidden in abundant of data. Furthermore, it has many features. Some of the features are redundant and some are less significant and they contribute little to the detection process. The purpose of this study is to identify an optimum number of significant features that can represent each category; Normal, Probe, U2R, R2L and DoS. Here, we deployed hierarchical feature selection approach and used similarity-based classification (Kohonen Self-Organizing Map) to classify an input data into their respective categories. Performance was measured based on their correct classification. Empirical results suggest that there is no generic feature subset which is suitable to represent all categories. Instead, different categories are best represented using different feature subsets.