Optimizing the Feature Set of Wireless Intrusion Detection Systems
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.