Abstract

Abstract A network intrusion detection method that integrates improved spatiotemporal residual network and generative adversarial network (GAN) in a big data environment is proposed to address the issues of poor feature extraction and significant impact from data imbalance in most existing intrusion detection methods. First, GANs are used for wireless sensor network data resampling to generate new sample sets, thereby overcoming the impact of data imbalance. Then, an improved spatiotemporal residual network model is designed, in which the spatial and temporal features of the data are extracted and fused through multi-scale one-dimensional convolution modules and gated loop unit modules, and identity maps are added based on the idea of residual networks to avoid network degradation and other issues. Finally, the resampled samples are input into the improved spatiotemporal residual network model to output the intrusion detection results of the network. Based on the NSL-KDD, UNSW-NB15, and CICIDS2017 datasets, experimental analysis is conducted on the proposed method. The results showed that its accuracy on the three datasets is 99.62, 83.98, and 99.86%, respectively, which are superior to other comparative methods.

Full Text

Published Version

Talk to us

Join us for a 30 min session where you can share your feedback and ask us any queries you have

Schedule a call

Disclaimer: All third-party content on this website/platform is and will remain the property of their respective owners and is provided on "as is" basis without any warranties, express or implied. Use of third-party content does not indicate any affiliation, sponsorship with or endorsement by them. Any references to third-party content is to identify the corresponding services and shall be considered fair use under The CopyrightLaw.