Feature selection-integrated classifier optimisation algorithm for network intrusion detection

In the era of technology, information security has gained significant importance, as intruders constantly conduct attacks to breach information systems. Intelligent network intrusion detection systems (NIDS) are promising for detecting malicious activities; however, it is required to apply feature selection (FS) and classifier optimisation (CO) using cost-effective algorithms to build an accurate and efficient system. Although classifier-dependent FS (CDFS) techniques and CO algorithms have been shown to perform well, they suffer from computational complexity, and their interdependencies negatively affect model performance. This study proposes the FS-integrated classifier optimisation algorithm that incorporates FS during CO, enhances optimisation, and tackles the interdependency problem. Furthermore, since this algorithm does not use an iterative feature selection process, such as forward selection or backward elimination, it provides relatively less complexity than other CDFS techniques. Moreover, an application of the proposed methodology (NIDS) was implemented using the designed framework to validate the model in this problem domain. The proposed methodology achieved accuracies of 85.10%, 73.24% with one feature for the NSLKDD datasets, 83.45% with 32 features for the UNSW-NB15 dataset, 99.41% with eight features, and 99.63% with 16 features for the CIC-IDS2017 datasets. The results showed that the FS-integrated optimisation algorithm had improved the accuracy of the classifier with fewer features. Furthermore, the proposed methodology outperformed other FS, ensemble learning, and deep learning-based methods regarding detection accuracy and false alarm rate. In conclusion, the developed NIDS is an accurate, efficient, straightforward, feasible, and easy-to-implement system that can be created using limited computing power and time as a promising solution to protect traditional and modern computer networks.