Malware Detection in IoT Networks Using Deep Learning Approach
IET Communications · 2026-01 · 20 (1)
DOI: 10.1049/cmu2.70143 ↗Kurz gefasst
Fachartikel in der Zeitschrift IET Communications, online erschienen am 08.04.2026. Verfasst von Inam Ullah und 5 weiteren Autor:innen. Die Arbeit nennt 54 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0).
Abstract (Originalsprache)
Internet of Things (IoT) devices are increasingly used for various applications, making them attractive targets for malware. This study investigates the detection of IoT malware using temporal convolutional networks (TCNs) to analyse the execution operation codes (OpCodes) of ARM‐based IoT applications. By leveraging a dataset of IoT applications comprising 281 malicious and 270 benign samples, we train TCN models to classify malware with high accuracy. A comparison with traditional machine learning models and results shows that the proposed TCN‐based approach achieves superior performance, with an accuracy of 98.6% in detecting new malware samples.
Zitieren
APA
Ullah, I., Jameel, A., Zada, I., Johar, S., Ali, A., & Tabassum, M. (2026). Malware Detection in IoT Networks Using Deep Learning Approach. IET Communications, 20(1). https://doi.org/10.1049/cmu2.70143
Vancouver
Ullah I, Jameel A, Zada I, Johar S, Ali A, Tabassum M. Malware Detection in IoT Networks Using Deep Learning Approach. IET Communications. 2026;20(1). doi:10.1049/cmu2.70143
BibTeX
@article{Ullah2026,
author = {Ullah, Inam and Jameel, Abid and Zada, Islam and Johar, Sumaira and Ali, Amjad and Tabassum, Mujahid},
title = {Malware Detection in IoT Networks Using Deep Learning Approach},
journal = {IET Communications},
year = {2026},
volume = {20},
number = {1},
doi = {10.1049/cmu2.70143}
}
EUVIMED