ExLightNet: A Lightweight and Explainable 1D-CNN for Real-Time Intrusion Detection in Resource-Constrained IoT Sensor Networks
Sensors · 06.11.2026 · 26 (21) · 7023
DOI: 10.3390/s26217023 ↗Kurz gefasst
Fachartikel in der Zeitschrift Sensors, online erschienen am 06.11.2026. Verfasst von Saman Iftikhar und 2 weiteren Autor:innen. Beteiligte Einrichtung: Faculty of Computer Studies, Arab Open University, Riyadh 84901, Saudi Arabia. Die Arbeit nennt 33 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: Arab Open University.
Abstract (Originalsprache)
Internet of Things (IoT) and Internet of Medical Things (IoMT) sensor deployments are pushing security decision-making from centralised servers towards resource-constrained edge gateways, where heavyweight deep learning detectors exceed the available compute, memory, and latency budgets, and where opaque alarms erode operator trust. This paper proposes ExLightNet, a lightweight one-dimensional convolutional neural network that couples depthwise-separable convolutions and squeeze-and-excitation channel attention with a tempered class-balanced training recipe (focal loss plus f−1 sampling) and per-channel INT8 weight quantisation, and attaches SHAP attributions directly to the deployed model. We evaluate the framework on the public RT-IoT2022 benchmark of 123,117 real bidirectional flows from smart-home and sensor IoT devices spanning nine attack behaviours and three normal device classes, an environment representative of the auxiliary sensing layer of home-based care settings. ExLightNet attains an attack-class recall (sensitivity) of 0.9976, missing only 40 of 16,592 attack flows, with macro-F1 0.9860 and AUC 0.9985 for binary attack detection (the 99.49% accuracy is retained for comparability with prior work, but accuracy is a misleading headline metric under the severe class imbalance of network traffic), and a macro-recall of 0.863 (97.70% accuracy, macro-F1 0.8621) across twelve fine-grained classes, surpassing a 4.5× larger standard CNN on the binary task while remaining within 0.0021 macro-F1 of Random Forest. Post-quantisation, the model shrinks from 162 KB to 37 KB (4.4×) with a macro-F1 drop of at most 0.007, sustaining 0.50 ms single-flow CPU latency, 66× faster than an accuracy-equivalent Random Forest. On a Raspberry Pi 4 gateway, the INT8 model sustains 2197 flow decisions per second across four Cortex-A72 cores, 21.4× faster than an accuracy-equivalent Random Forest, confirming the deployment profile on measured gateway-class hardware. SHAP analysis shows that forward payload statistics, backward header-size extremes, and packet-rate features dominate decisions, yielding operator-readable rationales.
Schlagwörter
Stichwörter der Autor:innen
Autor:innen und Institutionen
- Faculty of Computer Studies, Arab Open University, Riyadh 84901, Saudi Arabia.
- Department of Software Engineering, National University of Computer and Emerging Sciences, Islamabad, Chiniot-Faisalabad Campus, Chiniot 35400, Pakistan.
- Department of Computer Engineering, Gachon University, Seongnam 13120, Republic of Korea.
ORCID-Profile: Saman Iftikhar, Syed Rizwan Hassan
Förderung
- Arab Open University
Zitieren
APA
Iftikhar, S., Rafiq, A., & Hassan, S. R. (2026). ExLightNet: A Lightweight and Explainable 1D-CNN for Real-Time Intrusion Detection in Resource-Constrained IoT Sensor Networks. Sensors, 26(21), 7023. https://doi.org/10.3390/s26217023
Vancouver
Iftikhar S, Rafiq A, Hassan SR. ExLightNet: A Lightweight and Explainable 1D-CNN for Real-Time Intrusion Detection in Resource-Constrained IoT Sensor Networks. Sensors. 2026;26(21):7023. doi:10.3390/s26217023
BibTeX
@article{Iftikhar2026,
author = {Iftikhar, Saman and Rafiq, Ammar and Hassan, Syed Rizwan},
title = {ExLightNet: A Lightweight and Explainable 1D-CNN for Real-Time Intrusion Detection in Resource-Constrained IoT Sensor Networks},
journal = {Sensors},
year = {2026},
volume = {26},
number = {21},
pages = {7023},
doi = {10.3390/s26217023}
}
EUVIMED