Research on Webserver Data Tampering Attack Detection Method Based on Traffic Analysis
In order to improve the performance of Web server data tampering attack detection methods,a network anomaly traf-fic analysis and detection model is constructed by combining residual network(ResNet)and long short-term memory(LSTM)network.The experimental data show that the accuracy and detection rate of this model are 94.05％and 84.12％,respective-ly,which are superior to the other three traditional machine learning models.The network anomaly traffic detection system constructed by this model can detect import and export traffic in real-time.The accuracy of attack testing is about 94.43％,and the detection rate is 93.89％,meeting the requirements of system design.Research shows that combining machine learning and data mining algorithms for traffic analysis is an effective detection method that helps improve the security of Web server.
万方数据
维普
