Network Traffic Anomaly Detection Algorithm Based on Multi Feature Extraction Autoencoder
With the increasing level of complexity,automation and intelligence of network at-tacks,new types of attacks are constantly emerging in the network,which brings great challen-ges to feature code-based network attack detection and timely response.In order to identify ab-normal traffic more effectively and accurately,a network traffic anomaly detection algorithm based on multi-feature extraction self-encoder is proposed.The algorithm customizes a self-en-coder model based on multi-feature extraction,which consists of five different Encoder modules constituting the encoder and one Decoder module constituting the decoder,and is able to extract spatial and temporal features in the traffic at the same time,and can effectively avoid degrada-tion phenomenon,and effectively detect anomalous traffic.At the same time,the custom SMOTE-new sample oversampling method is used to solve the problem of data imbalance,and ANOVA is used for feature selection to optimize the data,reduce the complexity of the model,greatly shorten the detection time,and improve the detection of the algorithm in real time.The experimental results show that the proposed algorithm improves the accuracy of network traffic anomaly detec-tion by 1％compared with the current optimal algorithm of the same kind,and reduces the detection time by 4.22 s for millions of traffic data.
deep learningabnormal traffic detectionautoen-codersparse sample enhancementfeature selection
NETL
NSTL
万方数据
维普
