EUVIMEDEUVIMED entdecken
Open Access · CC BY 4.0

Adversarial Retraining for Machine Learning-Based Man-in-the-Middle Attack Detection in Smart Grid Industrial Control Systems

Md Mamunur Rashid, Shahriar Kaisar, Sakib Shahriar Shafin, Joarder Kamruzzaman, Tasadduq Imam

Machine Learning and Knowledge Extraction · 11.11.2026 · 8 (11) · 374

DOI: 10.3390/make8110374 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Machine Learning and Knowledge Extraction, online erschienen am 11.11.2026. Verfasst von Md Mamunur Rashid und 4 weiteren Autor:innen. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0).

AbstractBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Machine learning (ML)-based Intrusion Detection Systems (IDS) have become a key defence against advanced cyberattacks targeting Industrial Control Systems (ICS) in modern smart grids. Among these threats, Man-in-the-Middle (MITM) attacks are especially dangerous because they compromise the trust and privacy of communication between the control systems and other critical components within the interconnected smart grid. Although ML models have demonstrated a good ability to detect MITM attacks, they remain highly vulnerable to adversarial attacks, where small, carefully crafted changes can deceive the system and allow harmful traffic to go unnoticed. Even though adversarial machine learning is becoming increasingly important, its impact on ML-based MITM detection in smart grids remains inadequately explored. This paper examines the robustness of several widely used ML models against various adversarial attack methods using the RESLab smart grid dataset, an emulated testbed that produced network traffic containing MITM attack scenarios and is suitable for evaluating ML-based intrusion detection under adversarial conditions. To strengthen the models, we propose an adversarial training method that incorporates these hard-to-detect samples into the retraining process. Experiments show that adversarial attacks substantially degrade model performance. For example, fast-gradient sign method (FGSM)-perturbed MITM attacks can reduce the detection accuracy of the Random Forest (RF) classifier by 17.48 percentage points for binary classification and 14.86 percentage points for multiclass classification, demonstrating the vulnerability of conventional ML-based detection models. In contrast, when retrained with adversarial samples, the RF classifier achieves 81.59% detection accuracy for binary classification and 81.31% for multiclass classification, respectively, under fixed-source FGSM attacks, while maintaining strong performance on clean, unperturbed data. These results show that adversarial retraining greatly improves the robustness and reliability of ML-based MITM attack detection for protecting critical smart grid systems.

Zitieren

APA

Rashid, M. M., Kaisar, S., Shafin, S. S., Kamruzzaman, J., & Imam, T. (2026). Adversarial Retraining for Machine Learning-Based Man-in-the-Middle Attack Detection in Smart Grid Industrial Control Systems. Machine Learning and Knowledge Extraction, 8(11), 374. https://doi.org/10.3390/make8110374

Vancouver

Rashid MM, Kaisar S, Shafin SS, Kamruzzaman J, Imam T. Adversarial Retraining for Machine Learning-Based Man-in-the-Middle Attack Detection in Smart Grid Industrial Control Systems. Machine Learning and Knowledge Extraction. 2026;8(11):374. doi:10.3390/make8110374

BibTeX
@article{Rashid2026,
  author = {Rashid, Md Mamunur and Kaisar, Shahriar and Shafin, Sakib Shahriar and Kamruzzaman, Joarder and Imam, Tasadduq},
  title = {Adversarial Retraining for Machine Learning-Based Man-in-the-Middle Attack Detection in Smart Grid Industrial Control Systems},
  journal = {Machine Learning and Knowledge Extraction},
  year = {2026},
  volume = {8},
  number = {11},
  pages = {374},
  doi = {10.3390/make8110374}
}
Kostenlos starten →