A hybrid approach for feature selection using SFFS and SBFS with extra-tree and classification using XGBoost

Network data security is a global issue for governments, businesses, and individuals. The frequency of attacks is rapidly growing, and attackers' techniques are evolving. Many network security technologies utilise many techniques. An intrusion detection system (IDS) is a robust network security system that detects illegal and irregular network activity. This paper analyses feature selection methods and present an ensemble method to increase detection performance to address this issue. In the proposed model, we incorporate sequential forward floating selection (SFFS) with extra-tree and sequential backward floating selection (SBFS) with the extra-tree feature selection model by lowering the feature and XGBoost for higher classification accuracy. The proposed model achieves 98.68%, 98.94%, 95.25%, 99.91%, and 99.00% accuracy on the KDD'99, NSL-KDD, UNSW-NB15, CICIDS2017, and CICIDS2018 datasets. The comparative result analysis of proposed models outperforms other existing models in KDD'99, NSL-KDD, and UNSW-NB15 datasets in terms of accuracy, detection rate, and false alarm rate.