Network attack detection method, device and processor

The invention discloses a network attack detection method, a network attack detection device and a processor. The method comprises the following steps: performing feature extraction on received network traffic based on a feature extraction model to obtain a time feature vector and a data volume feature vector of the network traffic; performing attention processing on the time feature vector and the data volume feature vector based on an attention model to obtain a target feature vector; and detecting the time feature vector, the data volume feature vector and the target feature vector based on an attack detection model, and determining whether the network flow has a network attack, the attack detection model being a bidirectional recurrent neural network model. According to the method and the device, the technical problem of relatively poor accuracy of detecting the attack in the network flow in the related technology is solved. 本发明公开了一种网络攻击检测方法、装置和处理器。其中，该方法包括：基于特征提取模型对接收到的网络流量进行特征提取，得到网络流量的时间特征向量和数据量特征向量；基于