Research on Network Intrusion Detection Based on CNN-BiGRU-ResNet
Network intrusion detection is an important work in network security.It mainly judges the intrusion behavior through network,system and other information.It can detect the attack behavior in the network in time.The traditional network intru-sion detection method has the problems of low accuracy and high false alarm rate.Aiming at the above problems,a bi-directional gate control loop unit(BiGRU)is proposed.The method of network intrusion detection of convolutional neural network(CNN)and residual network(ResNet)is proposed.The method extracts the time series features by two-way gate control cycle unit and the local spatial features of convolutional neural network and residual network,and obtains the final classification results by using softmax classifier.The experiment shows that the method has better effect and higher accuracy than the GRU and RetNet based method.
国家科技期刊平台
NSTL
万方数据
