Automatic Feature Selection and Ensemble Classifier for Intrusion Detection

Abstract

Anomaly-based Intrusion Detection System (ADS) is one of the technologies widely used in network topology. Although many supervised and unsupervised learning methods in the field of machine learning have been used to improve the efficiency of ADS, achieving good performance is still a challenging problem for existing intrusion detection algorithms. Firstly, there are few public datasets available for evaluation. Secondly, a single classifier may not perform well in detecting each type of attack. Third, some of the existing schemes focus on feature subset selection, while ignoring the design of the classification decision algorithm, or focus on the classification decision algorithm. In order to address this issue, a new intrusion detection framework is proposed by comparing and studying various feature selection technologies and classification decision algorithms in this paper. An automatic parameter adjustment scheme is designed for feature selection and ensemble classification. It avoids the need to obtain the optimal parameters through manual experiments in advance, and can improve the robustness of the parameters and the model. We use the most classic NSL-KDD dataset and the latest CICIDS2018 dataset for comparative experiments. The experimental results demonstrate its efficiency in terms of Accuracy and False Positive Rate.