EUVIMEDEUVIMED entdecken
Open Access · CC BY 4.0

DEA-IDS: Drift-Aware Feature Selection and Few-Shot Adaptation for Cross-Domain IoT–IoMT Intrusion Detection

Büşra Günay iD, Mehmet Yavuz Yağcı iD

Sensors · 30.09.2026 · 26 (19) · 6200

DOI: 10.3390/s26196200 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Sensors, online erschienen am 30.09.2026. Verfasst von Büşra Günay und 1 weiteren Autor:innen. Beteiligte Einrichtung: Department of Computer Engineering, Faculty of Engineering and Natural Sciences, Istanbul Atlas University, 34408 Istanbul, Türkiye. Die Arbeit wurde bisher 1-mal zitiert (Crossref) und nennt 47 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0).

AbstractSchlagwörterBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Intrusion Detection Systems (IDSs) are essential for securing Internet of Things (IoT) and Internet of Medical Things (IoMT) environments, yet most machine learning-based IDSs assume that training and testing data follow similar distributions. In practice, domain shifts arising from differences in device characteristics, communication protocols, and traffic patterns can substantially increase false positive rates (FPRs), reducing operational reliability. This study proposes DEA-IDS (Drift-aware, Explainable and Adaptive Intrusion Detection System), a unified framework integrating SHAP-based explainability, statistical drift analysis via the Kolmogorov–Smirnov statistic and Wasserstein distance, drift-aware stable feature selection, and few-shot adaptation, evaluated on a CICIoT2023-to-CICIoMT2024 cross-domain transfer scenario. Under a leakage-free protocol in which drift statistics and few-shot samples are drawn exclusively from the target training split, DEA-IDS reduces FPR from 0.5468 to 0.0004 while maintaining an F1-score of 0.9944; threshold-, sample-size-, and feature-selection-control sensitivity analyses confirm this reduction reflects drift-aware stable feature selection rather than test-set leakage or dimensionality reduction alone. A per-attack-family analysis shows this improvement is concentrated in high-volume flood-style attacks and is accompanied by reduced detection of ARP spoofing, malformed-MQTT, and reconnaissance traffic, reported here as an explicit limitation. These results demonstrate that explicitly modeling feature stability before adaptation improves operational robustness for cross-domain intrusion detection in heterogeneous IoT–IoMT environments.

Schlagwörter

Stichwörter der Autor:innen

Internet of Medical Things (IoMT)cross-domain intrusion detectiondomain shiftdrift analysisexplainable artificial intelligence (XAI)few-shot learningintrusion detection systems (IDS)stable feature selection

Autor:innen und Institutionen

  • Department of Computer Engineering, Faculty of Engineering and Natural Sciences, Istanbul Atlas University, 34408 Istanbul, Türkiye.
  • Department of Computer Engineering, Faculty of Engineering, Istanbul University-Cerrahpaşa, 34320 Istanbul, Türkiye.

ORCID-Profile: Büşra Günay, Mehmet Yavuz Yağcı

Zitieren

APA

Günay, B., & Yağcı, M. Y. (2026). DEA-IDS: Drift-Aware Feature Selection and Few-Shot Adaptation for Cross-Domain IoT–IoMT Intrusion Detection. Sensors, 26(19), 6200. https://doi.org/10.3390/s26196200

Vancouver

Günay B, Yağcı MY. DEA-IDS: Drift-Aware Feature Selection and Few-Shot Adaptation for Cross-Domain IoT–IoMT Intrusion Detection. Sensors. 2026;26(19):6200. doi:10.3390/s26196200

BibTeX
@article{Gnay2026,
  author = {Günay, Büşra and Yağcı, Mehmet Yavuz},
  title = {DEA-IDS: Drift-Aware Feature Selection and Few-Shot Adaptation for Cross-Domain IoT–IoMT Intrusion Detection},
  journal = {Sensors},
  year = {2026},
  volume = {26},
  number = {19},
  pages = {6200},
  doi = {10.3390/s26196200}
}
Kostenlos starten →