A New Intrusion Detection Method Based on Adaptive Feature Extraction

Compared with traditional machine learning, intrusion detection based on deep learning has the advantage of feature extraction. Auto-encoders, owing to having good feature extraction and dimensionality reduction ability, are known for the superior performance. However, the network structure selection is time-consuming and laborious. The essential features cannot be automatically extracted according to different distribution characteristics of the data set. Moreover, the existing data pre-processing method fails to adapt the model better. Based on the stack sparse auto-encoders (SSAE), we propose a new intrusion detection model named DBSO-SSAE. The algorithm is based on difference brain storm optimization (DBSO) which automatically adapts to selection network framework. Meanwhile, a new normalization strategy is introduced to further improve the accuracy of the model. The simulation results show that DBSO-SSAE greatly reduces the complexity of manual tuning and increases the adaptability of the network model.