Scholarlink

<p>Smart Grids (SG) enhance efficiency and centralised control by enabling networked device communication, but these capabilities expose them to cyberattacks. Machine Learning (ML) and Deep Learning (DL) based Intrusion Detection Systems (IDS) have been employed to detect these threats. Yet, their adoption introduces new adversarial risks: specifically, attacks designed to fool IDS into misclassifying malicious activity as benign. In this study, we propose ADVIS-G, a novel, adversarially defended IDS framework for smart grids utilising deep learning. Our approach begins by training a high-accuracy (macro F1 96+%) classifier on session images from a DNP3-related dataset. We then assess vulnerability to adversarial examples generated using Fast Gradient Sign Method (FGSM), Basic Iterative Method (BIM), and Momentum Iterative Method (MIM) under varying perturbation rates. To counter such attacks, we introduce an adversarial blocking model based on autoencoder architectures that reconstruct input images, effectively removing adversarial perturbations. Experimental evaluation shows that under MIM, while the baseline model’s macro F1 drops to <InlineEquation ID="IEq1"> <EquationSource Format="TEX">\(\sim \)</EquationSource> </InlineEquation>0.5 (at <InlineEquation ID="IEq2"> <EquationSource Format="TEX">\(\epsilon \)</EquationSource> </InlineEquation>=0.1), adversarial training improves robustness to 0.7. Our proposed autoencoder-based blocking further increases the F1-score to <InlineEquation ID="IEq3"> <EquationSource Format="TEX">\(\sim \)</EquationSource> </InlineEquation>0.92 with RDU-Net, and <InlineEquation ID="IEq4"> <EquationSource Format="TEX">\(\sim \)</EquationSource> </InlineEquation>0.9 with U-Net. But the U-Net performed comparatively better under heavier attacks and normal images. Moreover, combining adversarial training with autoencoder defence achieves the highest resilience under stronger attacks. Additionally, MAE thresholding on reconstructions enables adversarial detection with an Area Under Curve (AUC) of 0.914 using RDU-Net and of 0.865 using U-Net. These results suggest that ADVIS-G significantly enhances IDS robustness against adversarial attacks, offering a promising direction for future smart grid security research.</p>

错误：搜索内容不能为空，请输入英文关键词
错误：关键词超出字数限制，请精简
高级检索

ADVIS-G: An Adversarially Defended Intrusion Detection System for Smart Grids Using Deep Learning

  • 期刊论文

  • 出版模式：

    开放获取

  • 发表日期：

    2026年3月1日

查看全文
  • Ramkrishna Acharya,
  • Loui Al Sardy,
  • Mamdouh Muhammad,
  • Reinhard German

摘要

Smart Grids (SG) enhance efficiency and centralised control by enabling networked device communication, but these capabilities expose them to cyberattacks. Machine Learning (ML) and Deep Learning (DL) based Intrusion Detection Systems (IDS) have been employed to detect these threats. Yet, their adoption introduces new adversarial risks: specifically, attacks designed to fool IDS into misclassifying malicious activity as benign. In this study, we propose ADVIS-G, a novel, adversarially defended IDS framework for smart grids utilising deep learning. Our approach begins by training a high-accuracy (macro F1 96+%) classifier on session images from a DNP3-related dataset. We then assess vulnerability to adversarial examples generated using Fast Gradient Sign Method (FGSM), Basic Iterative Method (BIM), and Momentum Iterative Method (MIM) under varying perturbation rates. To counter such attacks, we introduce an adversarial blocking model based on autoencoder architectures that reconstruct input images, effectively removing adversarial perturbations. Experimental evaluation shows that under MIM, while the baseline model’s macro F1 drops to \(\sim \) 0.5 (at \(\epsilon \) =0.1), adversarial training improves robustness to 0.7. Our proposed autoencoder-based blocking further increases the F1-score to \(\sim \) 0.92 with RDU-Net, and \(\sim \) 0.9 with U-Net. But the U-Net performed comparatively better under heavier attacks and normal images. Moreover, combining adversarial training with autoencoder defence achieves the highest resilience under stronger attacks. Additionally, MAE thresholding on reconstructions enables adversarial detection with an Area Under Curve (AUC) of 0.914 using RDU-Net and of 0.865 using U-Net. These results suggest that ADVIS-G significantly enhances IDS robustness against adversarial attacks, offering a promising direction for future smart grid security research.