基于CNN-BiGRU-ResNet的网络入侵检测研究

Research on Network Intrusion Detection Based on CNN-BiGRU-ResNet

网络入侵检测是网络安全中的一项重要工作,其主要是通过网络、系统等信息对入侵行为进行判断,它可以及时地发现网络中的攻击行为,传统的网络入侵检测方法存在准确率低并且误报率高的问题,针对上述问题,提出了一种融合双向门控循环单元(BiGRU)、卷积神经网络(CNN)以及残差网络(ResNet)的网络入侵检测方法,该方法通过双向门控循环单元对时间序列特征以及卷积神经网络和残差网络对局部空间特征的提取,利用softmax分类器获得最终的分类结果。实验表明,与基于GRU和ResNet等方法相比,该方法的网络入侵检测效果比较好,其准确率较高,误报率更低。

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.