Applications of Neural Networks in Network Intrusion Detection

Abstract

In this paper, we discuss the applications of multilayer perceptrons for classification of network intrusion detection data characterized by skewed class distributions. We compare several methods for learning from such skewed distributions by manipulating data records. The investigated methods include oversampling, undersampling and generating artificial data records using SMOTE technique. The presented methods are tested on KDDCup99 network intrusion dataset and compared using various classification performance metrics. In addition, the influence of decision margin on recall and misclassification rates is also examined