Network traffic anomaly detection method based on deep neural network

The invention discloses a network flow anomaly detection model and method based on a deep neural network, and the method comprises the steps: obtaining a data set, carrying out the feature extraction, obtaining benign common network attack data and system state data, and dividing the data into a training set and a test set according to a proportion of 8: 2; and training and testing are carried out through a built deep neural network model, so that a test identification result can be output, and finally the security situation of the whole network is evaluated. According to the method, a plurality of dimension feature indexes are mined from the network traffic, it is effectively verified that the deep neural network has good performance in network traffic anomaly detection, and a classification result is more accurate and reliable than a traditional machine learning method. The method has important practical application value in the field of network security monitoring. 本发明公开了基于深度神经网络的网络流量异常检测模型及方法，包括：获取数据集进行特征