Optimization of Smart Campus Cybersecurity and Student Privacy Protection Paths Based on Markov Models

Abstract

This paper starts with the application of hyper-convergence technology, builds the framework of a university smart campus based on it, and gives the framework description of the smart campus. In order to analyze the network security for the smart campus, the Markov model is used as the basis combined with the reinforced Q learning algorithm for network node security detection, and a specific simulation analysis is given. The encryption performance and defense performance of the elliptic curve cryptosystem are analyzed through the elliptic curve cryptosystem to formulate the encryption scheme for students’ private data in the smart campus. The results indicate that the Markov model node detection combined with reinforcement Q-learning in this paper takes a maximum time of about 5.75s when the network node size reaches 150. When the number of nodes in the smart campus network is 30, under brute force attack, the whole network is captured only when the number of malicious nodes increases to more than 22, while under random attack, it takes as many as 30 malicious nodes to join before the network completely falls. This illustrates that the use of the Markov model can be realized to analyze the network security of the smart campus and that student privacy protection needs to further improve the awareness of student data privacy protection and develop the habit of assessing the privacy risk beforehand in their daily network behavior.