A Hybrid Approach for Feature Selection in Improving the Efficiency of Wireless Intrusion Detection Systems

Intrusions are the result of flaws in the design and implementation of computer systems, operating systems, applications, and communication protocols. An intrusion detection system (IDS) is a device or software application that monitors network and/or system activities for malicious activities or policy violations and produces reports to a management station. In anomaly detection models, classifier is used as detectors. While constructing the classifier selection of the best set of the features is central to ensuring the performance, speed of learning, accuracy, and reliability of these detectors as well as to remove noise from the set of features. This paper proposes a novel hybrid model that efficiently selects the optimal set of features in order to detect 802.11-specific intrusions. Our model uses the Information Gain Ratio and K-Means classifier to compute and improve the accuracy of classifier. Experimental results clearly show that the optimization of a wireless feature set has a significant impact on the efficiency and accuracy of the intrusion detection system.