Abnormal Data Flow Detection in the Internet of Things

Abstract

In recent years, the Internet of things has developed rapidly, but the security problems are becoming more and more serious. Sensor nodes are important sources of data in the Internet of things. The abnormal and failure of sensing data in the Internet of Things will affect the connectivity of the network. If the accuracy and reliability of the corresponding perception data can be effectively improved, we can timely and accurately find out the emergency and monitor the working status of the network. Therefore, it is of great significance to detect the abnormal data of data streams in the sensor network nodes and confirm its source. Compared with traditional computers, the terminal devices in the perception layer of the Internet of things are more vulnerable to physical attacks. Aiming at the problems of abnormal traffic detection in Internet of things, 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. Combined with the above two methods, a sliding window abnormal traffic detection method based on the mixed dimension of time and space is proposed so as to further improve the detection accuracy and efficiency. The detection algorithm adopts the combination of machine learning and neural network. This detection method not only improves the accuracy of the final detection results, but also reduces the detection time and improves the detection efficiency.