On Detecting Abnormal Access for Online Ideological and Political Education

With the development and spread of networks, online education has become a new way in education. The online education platform encounters a large number of concurrent visiting, while the system must guarantee network security in the process of online education. The network visiting requests are real-time and dynamic in online education. In order to detect network intrusion and abnormal access in real time and adapt to the dynamic changes of network visiting requests, this paper adopts a data stream-based network intrusion detection method to monitor and manage online education visiting. First, a knowledge library is constructed by normal visiting mode and abnormal visiting mode. Second, the dissimilarity between data point and data cluster is used to measure the similarity between normal mode and abnormal mode. Lastly, the knowledge library is updated to reflect the changes of network in online education system by re-clustering. The proposed method is evaluated on a real dataset.