Research On Abnormal Traffic Detection Technology Based On Internet Of Things

The emergence of the Internet of Things has set off a new revolution in the global information industry.However,as the Internet of Things has become more widely used,the security issues have become more serious.Cyber attacks for the Internet of Things not only endanger the security of Internet of Things devices,but also seriously affect the security of the Internet.Therefore,how to detect abnormal traffic in the Io T environment becomes particularly important.Aiming at the problems of abnormal traffic detection based on the Internet of Things environment,this paper proposes an abnormal traffic detection method based on machine learning and sliding window and an abnormal traffic detection method based on neural network and sliding window.In order to further improve the detection accuracy and efficiency,a sliding window abnormal flow detection method based on the mixed dimensions of time and space is further proposed.The detection algorithm uses a combination of machine learning and neural networks.The detection method not only improves the accuracy of the final detection result,but also reduces the time overhead of the detection,and improves the detection efficiency.In summary,the main research results of this article are as follows:(1)An abnormal traffic detection method based on machine learning and sliding window is proposed,and the network data flows' characteristics of the sliding window based on the time dimension are studied,and the technical method of the expectation maximization algorithm clustering and then J48 machine learning classification is adopted,which effectively reduces the computational overhead.(2)An abnormal traffic detection method based on neural network and sliding window is proposed,and the network data flows' characteristics of sliding window based on spatial dimensions are studied.GRU neural network is used to analyze and detect network traffic,which effectively improves the detection rate,but it has larger computational overhead.(3)This paper summarizes the shortcomings of the above research results,and further proposes an abnormal flow detection technology based on the mixed dimensions of time and space and based on the sliding window.This technology firstly uses a sliding window based on the time dimension to extract features of network traffic.This technology uses J48 machine learning algorithm for the first detection and classification.The classified malicious traffic uses a sliding window based on spatial dimensions to re-extract features.This technology uses the GRU neural network algorithm to perform a second precise detection to further classify benign traffic and malicious traffic.This detection technology effectively improves the efficiency and accuracy of abnormal traffic detection,and has lower computational overhead.