MGNN-IDS: a multi-graph neural network approach for robust intrusion detection in the internet of things

Noha Alnazzawi (), Fatima Asiri (), Nazik Alturki (), Zhumabayeva Laula (), Saniya Zafar (), Shahid Latif () and Jawad Ahmad ()
Additional contact information
Noha Alnazzawi: Royal Commission for Jubail and Yanbu
Fatima Asiri: King Khalid University
Nazik Alturki: Princess Nourah bint Abdulrahman University
Zhumabayeva Laula: Yessenov University
Saniya Zafar: University of the West of England
Shahid Latif: University of the West of England
Jawad Ahmad: Prince Mohammad Bin Fahd University

Telecommunication Systems: Modelling, Analysis, Design and Management, 2025, vol. 88, issue 4, No 6, 20 pages

Abstract: Abstract The rapid development of Internet of Things (IoT) has led to the emergence of complex, heterogeneous, and large-scale networks that are increasingly vulnerable to sophisticated cyberattacks. Conventional Machine Learning (ML) and Deep Learning (DL) based intrusion detection models often struggle to capture the structural and relational dependencies inherent in IoT communications, as they rely heavily on flat feature spaces and have limited adaptability to dynamic network topologies. These limitations hinder cross-domain generalization and reduce detection accuracy in real-world IoT environments. To address these challenges, we propose a novel topology-aware Multi-Graph Neural Network (MGNN) architecture that efficiently models IoT networks by leveraging dual graph representations: a communication topology graph and a feature similarity graph. The MGNN employs Graph Convolutional Networks (GCNs) to extract topological patterns from network-level interactions and Graph Attention Networks (GATs) to learn complex semantic relationships between features. These representations are fused via an attention mechanism, producing a context-aware, high-fidelity embedding that enables accurate attack classification. Experimental results show that the proposed MGNN achieves 97.62% accuracy on the IDS-IoT 2024 dataset, outperforming the GCN-based model (84.29%) and the GAT-based model (90.47%). The MGNN also demonstrates strong generalizability, achieving 96.2% and 97.27% accuracy on the 5G-NIDD and IoT23 datasets, respectively, validating its robustness across dynamic IoT environments.

Keywords: Cybersecurity; Graph neural network; Intrusion detection system; Internet of things (search for similar items in EconPapers)
Date: 2025
References: Add references at CitEc
Citations:

Downloads: (external link)
http://link.springer.com/10.1007/s11235-025-01352-5 Abstract (text/html)
Access to the full text of the articles in this series is restricted.

Related works:
This item may be available elsewhere in EconPapers: Search for items with the same title.

Export reference: BibTeX RIS (EndNote, ProCite, RefMan) HTML/Text

Persistent link: https://EconPapers.repec.org/RePEc:spr:telsys:v:88:y:2025:i:4:d:10.1007_s11235-025-01352-5

Ordering information: This journal article can be ordered from
http://www.springer.com/journal/11235

DOI: 10.1007/s11235-025-01352-5

Access Statistics for this article

Telecommunication Systems: Modelling, Analysis, Design and Management is currently edited by Muhammad Khan

More articles in Telecommunication Systems: Modelling, Analysis, Design and Management from Springer
Bibliographic data for series maintained by Sonal Shukla () and Springer Nature Abstracting and Indexing ().