Mitigating Class Imbalance in Network Intrusion Detection with Feature-Regularized GANs

Jing Li, Wei Zong (), Yang-Wai Chow () and Willy Susilo
Additional contact information
Jing Li: Institute of Cybersecurity and Cryptology, School of Computing and Information Technology, University of Wollongong, Wollongong, NSW 2522, Australia
Wei Zong: Institute of Cybersecurity and Cryptology, School of Computing and Information Technology, University of Wollongong, Wollongong, NSW 2522, Australia
Yang-Wai Chow: Institute of Cybersecurity and Cryptology, School of Computing and Information Technology, University of Wollongong, Wollongong, NSW 2522, Australia
Willy Susilo: Institute of Cybersecurity and Cryptology, School of Computing and Information Technology, University of Wollongong, Wollongong, NSW 2522, Australia

Future Internet, 2025, vol. 17, issue 5, 1-20

Abstract: Network Intrusion Detection Systems (NIDS) often suffer from severe class imbalance, where minority attack types are underrepresented, leading to degraded detection performance. To address this challenge, we propose a novel augmentation framework that integrates Soft Nearest Neighbor Loss (SNNL) into Generative Adversarial Networks (GANs), including WGAN, CWGAN, and WGAN-GP. Unlike traditional oversampling methods (e.g., SMOTE, ADASYN), our approach improves feature-space alignment between real and synthetic samples, enhancing classifier generalization on rare classes. Experiments on NSL-KDD, CSE-CIC-IDS2017, and CSE-CIC-IDS2018 show that SNNL-augmented GANs consistently improve minority-class F1-scores without degrading overall accuracy or majority-class performance. UMAP visualizations confirm that SNNL produces more compact and class-consistent sample distributions. We also evaluate the computational overhead, finding the added cost moderate. These results demonstrate the effectiveness and practicality of SNNL as a general enhancement for GAN-based data augmentation in imbalanced NIDS tasks.

Keywords: network intrusion detection; WGAN; minority-class synthesis; soft nearest neighbor loss; data augmentation (search for similar items in EconPapers)
JEL-codes: O3 (search for similar items in EconPapers)
Date: 2025
References: Add references at CitEc
Citations:

Downloads: (external link)
https://www.mdpi.com/1999-5903/17/5/216/pdf (application/pdf)
https://www.mdpi.com/1999-5903/17/5/216/ (text/html)

Related works:
This item may be available elsewhere in EconPapers: Search for items with the same title.

Export reference: BibTeX RIS (EndNote, ProCite, RefMan) HTML/Text

Persistent link: https://EconPapers.repec.org/RePEc:gam:jftint:v:17:y:2025:i:5:p:216-:d:1654914

Access Statistics for this article

Future Internet is currently edited by Ms. Grace You

More articles in Future Internet from MDPI
Bibliographic data for series maintained by MDPI Indexing Manager ().