An effective intrusion detection system based on the FSA-BGRU hybrid model

Intrusion detection systems play a vital role in cyberspace security. In this study, a network intrusion detection method based on the feature selection algorithm (FSA) and a deep learning model is developed using a fusion of a recursive feature elimination (RFE) algorithm and a bidirectional gated recurrent unit (BGRU). Particularly, the RFE algorithm is employed to select features from high-dimensional data to reduce weak correlations between features and remove redundant features in the numerical feature space. Then, a neural network that combines the BGRU and multilayer perceptron (MLP) is adopted to extract deep intrusion behavior features. Finally, a support vector machine (SVM) classifier is used to classify intrusion behaviors. The proposed model is verified by experiments on the NSL-KDD dataset. The results indicate that the proposed model achieves a 90.25% accuracy and a 97.51% detection rate in binary classification and outperforms other machine learning and deep learning models in intrusion classification. The proposed method can provide new insight into network intrusion detection.