Deep Learning and Intelligent Perception

CLC number: TP393

An Augmentation Method for Small-Sample Imbalanced Industrial IoT Detection Data

小样本非平衡工业物联网检测数据扩增方法

¹ School of Cyber Science and Engineering, Wuhan University, Wuhan 430072, Hubei, China (武汉大学　国家网络安全学院，湖北　武汉　430072)
² Zhongnan Hospital, Wuhan University, Wuhan 430071, Hubei, China (武汉大学　中南医院，湖北　武汉　430071)

^† Corresponding author. E-mail: This email address is being protected from spambots. You need JavaScript enabled to view it. ; This email address is being protected from spambots. You need JavaScript enabled to view it.

Received: 20 June 2025

Abstract

IoT devices are highly vulnerable to cyberattacks due to their widespread, distributed nature and limited security features. Intrusion detection can counter these threats, but class imbalance between normal and abnormal traffic often degrades model performance. We propose a novel multi-generator adversarial data augmentation method that blends the strengths of TMG-GAN(Tabular Multi-Generator Generative Adversarial Network) and R3GAN (Re-GAN). Our approach uses multiple class-specific generators to create diverse, high-quality synthetic samples, improving training stability and minority-class detection. A dual-branch discriminator-classifier enhances authenticity and class prediction, while feature similarity and decoupling techniques ensure clear class separation. Experiments on TON-IoT and Edge-IIoTset datasets show our method outperforms existing techniques like hybrid sampling, SNGAN (Spectral Normalization GAN), and TMG-GAN, achieving higher detection accuracy and better minority-class recall for imbalanced IoT intrusion detection.

摘要

物联网设备由于其广泛分布和安全机制有限，极易成为网络攻击的目标。入侵检测能够缓解这些威胁，但正常与异常流量之间的类别不平衡常常导致模型性能下降。为此，本文结合TMG-GAN和R3GAN的优势，提出了一种新颖的多生成器对抗数据增强方法。该方法采用多个类别特定的生成器来生成多样且高质量的合成样本，从而提升训练稳定性和少数类检测能力。双分支判别器-分类器结构同时增强了样本真实性判别与类别预测，而特征相似性和解耦机制则确保了清晰的类别分离。在TON-IoT和Edge-IIoTset数据集上的实验结果表明，本文的方法优于现有的混合采样、SNGAN和TMG-GAN，在检测精度和少数类召回率方面均取得了更好的表现，有效应对了物联网入侵检测中的类别不平衡问题。