MACML: Marrying attention and convolution-based meta-learning method for few-shot IoT intrusion detection
PLOS One · 29.08.2025 · 20 (8) · e0331065
DOI: 10.1371/journal.pone.0331065 ↗Kurz gefasst
Evaluationsstudie in der Zeitschrift PLOS One, online erschienen am 29.08.2025. Verfasst von Congyuan Xu und 2 weiteren Autor:innen. Beteiligte Einrichtung: College of Artificial Intelligence, Jiaxing University, Jiaxing, Zhejiang, China. Hauptthemen laut MEDLINE: Internet of Things, Computer Security, Convolutional Neural Networks, Machine Learning. Die Arbeit wurde bisher 4-mal zitiert (Crossref) und nennt 46 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: National Natural Science Foundation of China, Zhejiang Provincial Natural Science Foundation of China, Jiaxing City Science and Technology Project.
Abstract (Originalsprache)
The widespread deployment of Internet of Things (IoT) devices has made them prime targets for cyberattacks. Existing intrusion detection systems (IDSs) heavily rely on large-scale labeled datasets, which limits their effectiveness in detecting novel attacks under few-shot scenarios. To address this challenge, we propose a meta-learning-based intrusion detection method called MACML (Marrying Attention and Convolution-based Meta-Learning). It integrates a self-attention mechanism to capture global dependencies and a convolutional neural network to extract local features, thereby enhancing the model’s overall perception of traffic characteristics. MACML adopts an optimization-based meta-learning framework that enables rapid adaptation to new tasks using only a small number of training samples, improving detection performance and generalization capability. We evaluate MACML on the CICIDS2018 and CICIoT2023 datasets. Experimental results show that, with only 10 training samples, MACML achieves an average accuracy of 98.75% and a detection rate of 99.17% on the CICIDS2018 dataset. On the CICIoT2023 dataset, it reaches 94.47% accuracy and a 95.32% detection rate, outperforming existing state-of-the-art methods.
Schlagwörter
MeSH-Schlagwörter (MEDLINE)
Autor:innen und Institutionen
- College of Artificial Intelligence, Jiaxing University, Jiaxing, Zhejiang, China.
- School of Electrical and Information Engineering, Tianjin University, Tianjin, China.
ORCID-Profile: Congyuan Xu, Jun Yang
Förderung
- National Natural Science Foundation of China
- Zhejiang Provincial Natural Science Foundation of China
- Jiaxing City Science and Technology Project
- China Postdoctoral Science Foundation
Zitieren
APA
Xu, C., Yang, J., & Li, P. (2025). MACML: Marrying attention and convolution-based meta-learning method for few-shot IoT intrusion detection. PLOS One, 20(8), e0331065. https://doi.org/10.1371/journal.pone.0331065
Vancouver
Xu C, Yang J, Li P. MACML: Marrying attention and convolution-based meta-learning method for few-shot IoT intrusion detection. PLOS One. 2025;20(8):e0331065. doi:10.1371/journal.pone.0331065
BibTeX
@article{Xu2025,
author = {Xu, Congyuan and Yang, Jun and Li, Panpan},
title = {MACML: Marrying attention and convolution-based meta-learning method for few-shot IoT intrusion detection},
journal = {PLOS One},
year = {2025},
volume = {20},
number = {8},
pages = {e0331065},
doi = {10.1371/journal.pone.0331065}
}
EUVIMED