Leveraging Graph Neural Networks for IoT Attack Detection
The widespread adoption of Internet of Things (IoT) devices in multiple sectors has driven technological progress; however, it has simultaneously rendered networks vulnerable to advanced cyber threats. Conventional intrusion detection systems face challenges adjusting to IoT environments' ever-...
Saved in:
| Main Authors: | , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
Sakarya University
2025-06-01
|
| Series: | Sakarya University Journal of Computer and Information Sciences |
| Subjects: | |
| Online Access: | https://dergipark.org.tr/en/download/article-file/4715498 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1839635079506165760 |
|---|---|
| author | Mevlüt Uysal Erdal Özdoğan Onur Ceran |
| author_facet | Mevlüt Uysal Erdal Özdoğan Onur Ceran |
| author_sort | Mevlüt Uysal |
| collection | DOAJ |
| description | The widespread adoption of Internet of Things (IoT) devices in multiple sectors has driven technological progress; however, it has simultaneously rendered networks vulnerable to advanced cyber threats. Conventional intrusion detection systems face challenges adjusting to IoT environments' ever-changing and diverse characteristics. To address this challenge, researchers propose a novel hybrid approach combining Graph Neural Networks and XGBoost algorithm for robust intrusion detection in IoT ecosystems. This paper presents a comprehensive methodology for integrating GNNs and XGBoost in IoT intrusion detection and evaluates its effectiveness using diverse datasets. The proposed model preprocesses data by standardization, handling missing values, and encoding categorical features. It leverages GNNs to model spatial dependencies and interactions within IoT networks and utilizes XGBoost to distill complex features for predictive analysis. The late fusion technique combines predictions from both models to enhance overall performance. Experimental results on four datasets, including CICIoT-2023, CICIDS-2017, UNSW-NB15, and IoMT-2024, demonstrate the efficacy of the hybrid model. High accuracy, precision, recall, and AUC values indicate the model's robustness in detecting attacks while minimizing false alarms. The study advances IoT security by introducing synergistic solutions and provides practical insights for implementing intrusion detection systems in real-world IoT environments. |
| format | Article |
| id | doaj-art-a53529f43f3d42a4ac41901904d0aad8 |
| institution | Matheson Library |
| issn | 2636-8129 |
| language | English |
| publishDate | 2025-06-01 |
| publisher | Sakarya University |
| record_format | Article |
| series | Sakarya University Journal of Computer and Information Sciences |
| spelling | doaj-art-a53529f43f3d42a4ac41901904d0aad82025-07-09T12:52:59ZengSakarya UniversitySakarya University Journal of Computer and Information Sciences2636-81292025-06-018222324410.35377/saucis...166343528Leveraging Graph Neural Networks for IoT Attack DetectionMevlüt Uysal0https://orcid.org/0000-0002-6934-4421Erdal Özdoğan1https://orcid.org/0000-0002-3339-0493Onur Ceran2https://orcid.org/0000-0003-2147-0506GAZI UNIVERSITYULUDAG UNIVERSITYGAZİ ÜNİVERSİTESİThe widespread adoption of Internet of Things (IoT) devices in multiple sectors has driven technological progress; however, it has simultaneously rendered networks vulnerable to advanced cyber threats. Conventional intrusion detection systems face challenges adjusting to IoT environments' ever-changing and diverse characteristics. To address this challenge, researchers propose a novel hybrid approach combining Graph Neural Networks and XGBoost algorithm for robust intrusion detection in IoT ecosystems. This paper presents a comprehensive methodology for integrating GNNs and XGBoost in IoT intrusion detection and evaluates its effectiveness using diverse datasets. The proposed model preprocesses data by standardization, handling missing values, and encoding categorical features. It leverages GNNs to model spatial dependencies and interactions within IoT networks and utilizes XGBoost to distill complex features for predictive analysis. The late fusion technique combines predictions from both models to enhance overall performance. Experimental results on four datasets, including CICIoT-2023, CICIDS-2017, UNSW-NB15, and IoMT-2024, demonstrate the efficacy of the hybrid model. High accuracy, precision, recall, and AUC values indicate the model's robustness in detecting attacks while minimizing false alarms. The study advances IoT security by introducing synergistic solutions and provides practical insights for implementing intrusion detection systems in real-world IoT environments.https://dergipark.org.tr/en/download/article-file/4715498gnniot idsxgboostipsiot security |
| spellingShingle | Mevlüt Uysal Erdal Özdoğan Onur Ceran Leveraging Graph Neural Networks for IoT Attack Detection Sakarya University Journal of Computer and Information Sciences gnn iot ids xgboost ips iot security |
| title | Leveraging Graph Neural Networks for IoT Attack Detection |
| title_full | Leveraging Graph Neural Networks for IoT Attack Detection |
| title_fullStr | Leveraging Graph Neural Networks for IoT Attack Detection |
| title_full_unstemmed | Leveraging Graph Neural Networks for IoT Attack Detection |
| title_short | Leveraging Graph Neural Networks for IoT Attack Detection |
| title_sort | leveraging graph neural networks for iot attack detection |
| topic | gnn iot ids xgboost ips iot security |
| url | https://dergipark.org.tr/en/download/article-file/4715498 |
| work_keys_str_mv | AT mevlutuysal leveraginggraphneuralnetworksforiotattackdetection AT erdalozdogan leveraginggraphneuralnetworksforiotattackdetection AT onurceran leveraginggraphneuralnetworksforiotattackdetection |