Network intrusion detection method based on space-time feature fusion

Abstract

The invention discloses a network intrusion detection method based on space-time feature fusion. The method comprises: establishing a convolutional neural network with a plurality of convolution kernels of different scales to be connected with a fusion detection model of a long-term and short-term memory network; carrying out spatial domain feature extraction on the network traffic data to be detected by adopting a convolutional neural network with a plurality of different scale convolution kernels, and then continuously carrying out time domain feature extraction by adopting a long and shortterm memory network; and then carrying out pooling operation, and finally carrying out classification processing on the to-be-detected network traffic data fused with the spatial domain features and the time domain features by combining a classifier. The method has higher accuracy, lower false alarm rate and missing report rate and excellent generalization capability when processing a public dataset with high dimension, nonlinearity and large data volume.

Description

technical field [0001] The invention belongs to the field of network traffic intrusion detection, relates to a deep learning neural network algorithm, and specifically relates to a network intrusion detection method based on spatio-temporal feature fusion, which efficiently classifies network intrusions under the background of large traffic. Background technique [0002] In recent years, the flow of information in cyberspace has been increasing at an alarming rate every year, and the issue of network information security has received more and more attention in recent years, and the establishment of intrusion detection models based on machine learning algorithms is currently the most mainstream research direction. [0003] In the early days of research, supervised or unsupervised traditional machine learning algorithms achieved excellent classification results when dealing with data sets with a small amount of data and low dimensions. However, with the expansion of network c...

AI Technical Summary

Problems solved by technology

However, with the expansion of network capacity, unlabeled, nonlinear, and high-dimensional network simulation data sets have emerged, and the advantages of traditional machine learning algorithms no longer exist. The algorithm has high redundancy, long computing time, and low detection accuracy. Continuous decline

Images