Industrial Control System Intrusion Detection Based on Feature Selection and Temporal Convolutional Network

Aiming at the problem of feature redundancy in industrial control system traffic data and the poor detection ability of deep learning models for small-scale data sets, an industrial control system intrusion detection model based on feature selection and temporal convolutional networks was proposed. First, the abnormal features and sample imbalance data of the source domain dataset were processed to improve the quality of the source domain dataset. Secondly, in view of the feature redundancy of traffic data, a IGR–PCA feature selection algorithm was constructed by using the information gain rate and principal component analysis method, and the optimal feature subset was selected to achieve data dimensionality reduction. Then, according to the time series characteristics of industrial control system traffic data, the excellent processing ability of temporal convolution network (TCN) for time series data was used to construct a source domain temporal convolution network pretrained model on a large-scale source domain data set. Finally, combined with the transfer learning (TL) fine-tuning strategy, the traffic characteristics of the source domain sample data were obtained on a small-scale target domain dataset, and the target domain TCN–TL model was constructed. The experimental test was carried out using the public industrial control system data set. The experimental results showed that compared with other methods, the proposed method can reduce the data dimension and reduce the calculation amount while still having a superior detection effect. The model proposed in this paper has achieved good detection results on both large-scale source domain data sets and small-scale target domain data sets. In the target domain, the transfer learning fine-tuning strategy can be used to learn the knowledge in the source domain, and the detection accuracy rate is 99.06%. In the training time comparison, the proposed model consumes less training time. Meanwhile, it also has better generalization ability and can better protect the security of industrial control systems. © 2022 Editorial Department of Journal of Sichuan University. All rights reserved.