Deep Learning Applications for Intrusion Detection in Network Traffic

This paper discusses the problems of applying deep learning methods for intrusion detection in network traffic. The results of analyzing the relevant studies and reviews of deep learning applications for intrusion detection are presented. The most popular deep learning methods are discussed and compared. A classification system of deep learning methods for intrusion detection is proposed. The current trends and challenges of applying deep learning methods for intrusion detection in network traffic are identified. To assess the applicability of deep learning methods for intrusion detection, the CNN-BiLSTM neural network is synthesized. The synthesized network is compared with the previously developed model based on the random forest classifier. The deep learning method makes it possible to simplify the feature engineering stage, with the values of quality metrics for the random forest and CNN-BiLSTM models being close. This confirms the high prospects for application of deep learning methods to intrusion detection.