A novel boundary adaptive oversampling approach for intrusion detection

Abstract

Managing unbalanced datasets is a significant challenge in intrusion detection, since uncommon assaults are often obscured by the bulk of regular network traffic. In order to mitigate the effects of class imbalance and improve intrusion detection system (IDS) performance, it is necessary to use a variety of imbalanced learning algorithms. Methods of data augmentation such as adaptive synthetic sampling (ADASYN) and synthetic minority oversampling technique (SMOTE) are useful in addressing class imbalance. This paper introduces a novel technique to data resampling where decision tree-generated decision boundaries are used to conduct ADASYN on complicated and unusual samples. When this method’s efficacy was evaluated using the standard NSL-KDD dataset, the accuracy of the unusual class u2r was increased to 42% and, for r2l it was improved to 83%, respectively. The UNSW-NB 15 dataset has been used for further validation of the method, and its statistical significance has been asserted by comparing the suggested method to other oversampling techniques.