To solve the problems that the network intrusion detection system in the Internet of things couldn't identify new attacks and has limited flexibility,a network intrusion detection system based on honeyfarm was proposed,which could effectively identify abnormal traffic and have continuous learning ability.Firstly,considering the characteristics of the convolutional block attention module,an abnormal traffic detection model was developed,focusing on both channel and spatial dimensions,to enhance the model's recognition abilities.Secondly,a model training scheme utilizing federat-ed learning was employed to enhance the model's generalization capabilities.Finally,the abnormal traffic detection mod-el at the edge nodes was continuously updated and iterated based on the honeyfarm,so as to improve the system's accu-racy in recognizing new attack traffic.The experimental results demonstrate that the proposed system not only effectively detects abnormal behavior in network traffic,but also continually enhances performance in detecting abnormal traffic.
维普
万方数据