To defend against DoS attacks and ensure QoS of web server, we first propose an efficient network anomaly detection method based on TCM-KNN (Transductive Confidence Machines for K-Nearest Neighbors) algorithm. Secondly, we integrate a lot of objective and efficient DoS impact metrics from the perceptions of the end users into TCM-KNN algorithm to build a robust anomaly detection mechanism. Finally, Genetic Algorithm (GA) based instance selection method is introduced to boost the real-time detection performance of our method.
CBFS: A Clustering-Based Feature Selection Mechanism for Network Anomaly Detection
