GUCN: A machine learning model combining time series features for malicious network behavior detection

Malicious network behaviors significantly impact network and information security, the intelligent detection of network malicious behavior is an important work in the field of information and privacy protection. Traditional machine learning methods have achieved certain results in solving this problem, but generally ignore the continuous characteristics of malicious network behavior in time series. Aiming at this weakness, this paper proposes a Gated Unit Convolutional Networks (GUCN) model based on gated recurrent unit and convolutional neural network. Meanwhile, it also uses the feature screening method of random forest and the data dimension reduction method of UMAP to process the high dimensional data, which reduces the data redundancy. The results show that the method can effectively detect malicious network behavior, and because it can learn the objective characteristics of behavior in time series, it has the potential to identify malicious attack behavior in advance.