To search, Click below search items.


All Published Papers Search Service


Optimizing the Feature Set of Wireless Intrusion Detection Systems


Mouhcine Guennoun, Aboubakr Lbekkouri, Khalil El-Khatib


Vol. 8  No. 10  pp. 127-131


Intrusion detection in wireless networks has gained considerable attention in the last few years. Wireless networks are not only susceptible to TCP/IP-based attacks native to wired networks, they are also subject to a wide array of 802.11-specific threats. Such treats range from passive eavesdropping to more devastating denial of service attacks. To detect these intrusions classifiers are built to distinguish between normal and anomalous traffic. It has been proved that optimizing the feature set has a major impact on the performance, speed of learning, accuracy and reliability of the intrusion detection system. Unfortunately, current wireless intrusion detection solutions rely on features extracted directly from the frame headers to build the learning algorithm of the classifiers. In this paper, we propose a hybrid model that efficiently selects the optimal set of features in order to detect 802.11 specific intrusions. In our approach, the wireless fame attributes are first ranked according to a score assigned by the information gain ratio measure. K-means classifier is then used to build the optimal subset of features that maximizes the accuracy of the detectors while reducing their learning time.


Feature Selection, Intrusion Detection Systems, K-means, Information Gain Ratio, Wireless Networks