Research on Intrusion Detection Based on BP Neural Network

The purpose of network security is to prevent the data transmitted over the Internet from being stolen and tampered with, and to ensure the security of the data. It is not only necessary to ensure that the information entering and exiting the network is not stolen or tampered with, but also to ensure the integrity and confidentiality of the information in the information system. The network environment is becoming more and more complex, and the attack methods are becoming more and more diverse. Therefore, intrusion detection systems have some common problems, such as low detection rate and high false alarm rate, and it is difficult to meet the real-time requirements of intrusion detection systems. Currently, deep learning is increasingly used in intrusion detection. In order to solve the problems existing in the current intrusion detection system, this paper studies the application of deep learning in intrusion detection. First, it analyzes the BP neural network (BP-NN) technology, and proposes an improvement method for the shortcomings of the current BP-NN, and finally conducts an empirical analysis. Experimental results show that intrusion detection based on BP-NN has a high accuracy rate, and the false alarm rate and false alarm rate are both at a low level.