Research On Network Intrusion Detection Based On On Deep Learning

With the development of network interconnection,network security issues have attracted a lot of attention.Diversified network intrusion methods have put forward higher requirements for network intrusion detection technology.At present,the main problem faced in the research of intrusion detection technology is the challenge that the increasing network traffic poses to the data processing capability of intrusion detection.Based on deep learning related theories,this article carries out related research on network intrusion detection.The specific work is as follows:This article first analyzes the UNSW-NB15 data set,performs pre-processing operations such as feature extraction,numericalization,and normalization,and then inputs it into the corresponding neural network intrusion detection model to carry out simulation experiments,as follows:(1)The use of RNN to construct an intrusion detection model is compared with the KNN and SVM models.The experimental results show that the RNN-based intrusion detection model has achieved good results in four indicators: accuracy,precision,recall,and F-1;(2)Build an intrusion detection model using GNN neural network improved by RNN,and optimize it with Adam optimizer.Compare experiments with RNN and LSTM models based on different optimizers.The results of simulation experiments show that On the four indicators of recall rate and F-1,the GRU neural network intrusion detection model based on Adam optimization performs well.In this paper,the deep learning model is applied to network intrusion detection.The research results show that the intrusion detection method based on deep learning has achieved good detection results,and will continue to carry out in-depth research in this field in the future.