Towards Efficient Features Dimensionality Reduction for Network Intrusion Detection on Highly Imbalanced Traffic

Abstract

The performance of an IDS is significantly improved when the features are more discriminative and representative. This research effort is able to reduce the CICIDS2017 dataset’s feature dimensions from 81 to 10, while maintaining a high accuracy of 99.6% in multi-class and binary classification. Furthermore, we propose a Multi-Class Combined performance metric CombinedMc with respect to class distribution to compare various multi-class and binary classification systems through incorporating FAR, DR, Accuracy, and class distribution parameters. In addition, we developed a uniform distribution based balancing approach to handle the imbalanced distribution of the minority class instances in the CICIDS 2017 network intrusion dataset.