Campus Network Intrusion Detection Method Based on Convolutional Neural Network in Big Data Environment

Abstract

In the big data (BD) environment, network intrusion detection (NID) technology has become a research hotspot at home and abroad. As one of the important components of the computer system network, the campus network (CN) has attracted more and more attention to its security risks. How to effectively prevent CN viruses from invading other places and ensuring normal operation has become one of the current topics that need to be solved and valued urgently. With the rapid development of computer technology, CN is essential for teachers and students to study and live in school. There are a large number of information resources in the campus, various professional classrooms and other public areas for information sharing through the CN. As a deep learning algorithm, convolutional neural network (CCN) can simulate the multi-layer neural network structure of the human brain to understand complex information. This paper adopts experimental analysis method and data analysis method, and intends to construct a CN intrusion detection (CNID) model CNN-IDM based on CCN through experimental research, so as to improve the efficiency of CNID. According to the experimental results, the model detection accuracy rate of this experiment is higher than other methods and models, and the false alarm rate is also far lower than other methods. It has good detection performance and can meet the basic needs of CNID.