{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,2,11]],"date-time":"2026-02-11T18:25:25Z","timestamp":1770834325018,"version":"3.50.1"},"reference-count":26,"publisher":"MDPI AG","issue":"2","license":[{"start":{"date-parts":[[2026,2,11]],"date-time":"2026-02-11T00:00:00Z","timestamp":1770768000000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["Computers"],"abstract":"<jats:p>The integration of Federated Learning (FL) and Graph Neural Networks (GNNs) has emerged as a promising paradigm for distributed intelligence in Internet of Things (IoT) environments. However, challenges related to trust, device heterogeneity, and energy efficiency continue to hinder scalable deployment in real-world settings. This paper presents Trust-FedGNN, a trust-aware federated graph learning framework that jointly addresses reliability, robustness, and sustainability in IoT ecosystems. The framework combines reliability-based reputation modeling, energy-aware client scheduling, and dynamic graph pruning to reduce communication overhead and energy consumption during collaborative training, while mitigating the influence of unreliable or malicious participants. Trust evaluation is explicitly decoupled from energy availability, ensuring that honest but resource-constrained devices are not penalized during aggregation. Experimental results on benchmark IoT datasets demonstrate up to 5.8% higher accuracy, 3.1% higher F1-score, and approximately 22% lower energy consumption compared with State-of-the-Art federated baselines, while maintaining robustness under partial adversarial participation. These results confirm the effectiveness of Trust-FedGNN as a secure, robust, and energy-efficient federated graph learning solution for heterogeneous IoT networks (a proof-of-concept evaluation across 10 federated clients).<\/jats:p>","DOI":"10.3390\/computers15020121","type":"journal-article","created":{"date-parts":[[2026,2,11]],"date-time":"2026-02-11T17:45:36Z","timestamp":1770831936000},"page":"121","update-policy":"https:\/\/doi.org\/10.3390\/mdpi_crossmark_policy","source":"Crossref","is-referenced-by-count":0,"title":["Trust-Aware Federated Graph Learning for Secure and Energy-Efficient IoT Ecosystems"],"prefix":"10.3390","volume":"15","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-8872-5721","authenticated-orcid":false,"given":"Manuel J. C. S.","family":"Reis","sequence":"first","affiliation":[{"name":"Engineering Department and IEETA, University of Tr\u00e1s-os-Montes e Alto Douro, Quinta de Prados, 5000-801 Vila Real, Portugal"}]}],"member":"1968","published-online":{"date-parts":[[2026,2,11]]},"reference":[{"key":"ref_1","doi-asserted-by":"crossref","unstructured":"Dritsas, E., and Trigka, M. (2025). Federated Learning for IoT: A Survey of Techniques, Challenges, and Applications. J. Sens. Actuator Netw., 14.","DOI":"10.3390\/jsan14010009"},{"key":"ref_2","doi-asserted-by":"crossref","unstructured":"Khajehali, N., Yan, J., Chow, Y.-W., and Fahmideh, M. (2023). A Comprehensive Overview of IoT-Based Federated Learning: Focusing on Client Selection Methods. Sensors, 23.","DOI":"10.3390\/s23167235"},{"key":"ref_3","doi-asserted-by":"crossref","first-page":"1","DOI":"10.58496\/BJIoT\/2023\/001","article-title":"Federated Learning in IoT: A Survey on Distributed Decision Making","volume":"2023","author":"Hameed","year":"2023","journal-title":"Babylon. J. Internet Things"},{"key":"ref_4","doi-asserted-by":"crossref","first-page":"1","DOI":"10.31449\/inf.v49i17.7707","article-title":"A Survey of Federated Learning for IoT: Addressing Resource Constraints and Heterogeneous Challenges","volume":"49","author":"Vashisth","year":"2025","journal-title":"Informatica"},{"key":"ref_5","doi-asserted-by":"crossref","unstructured":"Yang, Q., Fan, L., and Yu, H. (2020). Threats to Federated Learning. Federated Learning: Privacy and Incentive, Springer International Publishing.","DOI":"10.1007\/978-3-030-63076-8"},{"key":"ref_6","doi-asserted-by":"crossref","unstructured":"Nalinipriya, G., Lydia, E.L., Sree, S.R., Nikolenko, D., Potluri, S., Ramesh, J.V.N., and Jayachandran, S. (2024). Optimal Directed Acyclic Graph Federated Learning Model for Energy-Efficient IoT Communication Networks. Sci. Rep., 14.","DOI":"10.1038\/s41598-024-71995-y"},{"key":"ref_7","doi-asserted-by":"crossref","unstructured":"Wang, L., Li, Y., and Zuo, L. (2024). Trust Management for IoT Devices Based on Federated Learning and Blockchain. J. Supercomput., 81.","DOI":"10.1007\/s11227-024-06715-4"},{"key":"ref_8","doi-asserted-by":"crossref","first-page":"1011","DOI":"10.1007\/s11633-024-1510-8","article-title":"A Comprehensive Survey on Trustworthy Graph Neural Networks: Privacy, Robustness, Fairness, and Explainability","volume":"21","author":"Dai","year":"2024","journal-title":"Mach. Intell. Res."},{"key":"ref_9","doi-asserted-by":"crossref","first-page":"2226","DOI":"10.1109\/COMST.2025.3613845","article-title":"Graph Neural Networks for Next-Generation-IoT: Recent Advances and Open Challenges","volume":"28","author":"Hanzo","year":"2026","journal-title":"IEEE Commun. Surv. Tutor."},{"key":"ref_10","doi-asserted-by":"crossref","unstructured":"Alahmari, S., and Alghamdi, I. (2025). A Comprehensive Survey on Energy-Efficient and Privacy-Preserving Federated Learning for Edge Intelligence and IoT. Results Eng., 28.","DOI":"10.1016\/j.rineng.2025.107849"},{"key":"ref_11","doi-asserted-by":"crossref","unstructured":"Akhtarshenas, A., Vahedifar, M.A., Ayoobi, N., Maham, B., Alizadeh, T., Ebrahimi, S., and L\u00f3pez-P\u00e9rez, D. (2024). Federated Learning: A Cutting-Edge Survey of the Latest Advancements and Applications. Comput. Commun., 228.","DOI":"10.1016\/j.comcom.2024.107964"},{"key":"ref_12","doi-asserted-by":"crossref","first-page":"1","DOI":"10.1145\/3565973","article-title":"Graph Neural Networks in IoT: A Survey","volume":"19","author":"Dong","year":"2023","journal-title":"ACM Trans. Sens. Netw."},{"key":"ref_13","doi-asserted-by":"crossref","unstructured":"Fotia, L., Delicato, F., and Fortino, G. (2023). Trust in Edge-Based Internet of Things Architectures: State of the Art and Research Challenges. ACM Comput. Surv., 55.","DOI":"10.1145\/3558779"},{"key":"ref_14","doi-asserted-by":"crossref","unstructured":"Wang, M.-J.-S., Xu, S.-H., Jiang, J.-C., Xiang, D., and Hsieh, S.-Y. (2026). Global Reliable Diagnosis of Networks Based on Self-Comparative Diagnosis Model and g-Good-Neighbor Property. J. Comput. Syst. Sci., 155.","DOI":"10.1016\/j.jcss.2025.103698"},{"key":"ref_15","doi-asserted-by":"crossref","unstructured":"Jiang, Y., Ma, B., Wang, X., Yu, G., Yu, P., Wang, Z., Ni, W., and Liu, R.P. (2024). Blockchained Federated Learning for Internet of Things: A Comprehensive Survey. ACM Comput. Surv., 56.","DOI":"10.1145\/3659099"},{"key":"ref_16","doi-asserted-by":"crossref","unstructured":"Cao, Y., Liu, D., Zhang, S., Wu, T., Xue, F., and Tang, H. (2024). T-FedHA: A Trusted Hierarchical Asynchronous Federated Learning Framework for Internet of Things. Expert Syst. Appl., 245.","DOI":"10.1016\/j.eswa.2023.123006"},{"key":"ref_17","doi-asserted-by":"crossref","unstructured":"Xu, J., Zhang, C., Jin, L., and Su, C. (2025). A Trust-Aware Incentive Mechanism for Federated Learning with Heterogeneous Clients in Edge Computing. J. Cybersecurity Priv., 5.","DOI":"10.3390\/jcp5030037"},{"key":"ref_18","doi-asserted-by":"crossref","unstructured":"Zhou, A., Yang, J., Qi, Y., Shi, Y., Qiao, T., Zhao, W., and Hu, C. (2023, January 9\u201313). Hardware-Aware Graph Neural Network Automated Design for Edge Computing Platforms. Proceedings of the 2023 60th ACM\/IEEE Design Automation Conference (DAC), San Francisco, CA, USA.","DOI":"10.1109\/DAC56929.2023.10247875"},{"key":"ref_19","doi-asserted-by":"crossref","unstructured":"Xia, J., Zhang, Y., and Shi, Y. (2025). Towards Energy-Aware Federated Learning via MARL: A Dual-Selection Approach for Model and Client. Proceedings of the 43rd IEEE\/ACM International Conference on Computer-Aided Design, Association for Computing Machinery.","DOI":"10.1145\/3676536.3676815"},{"key":"ref_20","doi-asserted-by":"crossref","first-page":"131","DOI":"10.1016\/j.comcom.2024.04.012","article-title":"Towards Energy-Aware Federated Learning via Collaborative Computing Approach","volume":"221","author":"Arouj","year":"2024","journal-title":"Comput. Commun."},{"key":"ref_21","doi-asserted-by":"crossref","unstructured":"Baqer, M. (2025). Energy-Efficient Federated Learning for Internet of Things: Leveraging In-Network Processing and Hierarchical Clustering. Future Internet, 17.","DOI":"10.3390\/fi17010004"},{"key":"ref_22","doi-asserted-by":"crossref","unstructured":"Moustafa, N., Ahmed, M., and Ahmed, S. (2020\u20131, January 29). Data Analytics-Enabled Intrusion Detection: Evaluations of ToN_IoT Linux Datasets. Proceedings of the 2020 IEEE 19th International Conference on Trust, Security and Privacy in Computing and Communications (TrustCom), Guangzhou, China.","DOI":"10.1109\/TrustCom50675.2020.00100"},{"key":"ref_23","unstructured":"Garcia, S., Parmisano, A., and Erquiaga, M.J. (2020). IoT-23: A Labeled Dataset with Malicious and Benign IoT Network Traffic, Zenodo."},{"key":"ref_24","doi-asserted-by":"crossref","unstructured":"Chen, D., Tan, V.J., Lu, Z., Wu, E., and Hu, J. (2023, January 17\u201324). OpenFed: A Comprehensive and Versatile Open-Source Federated Learning Framework. Proceedings of the 2023 IEEE\/CVF Conference on Computer Vision and Pattern Recognition Workshops (CVPRW), Vancouver, BC, Canada.","DOI":"10.1109\/CVPRW59228.2023.00530"},{"key":"ref_25","unstructured":"McMahan, B., Moore, E., Ramage, D., Hampson, S., and Arcas, B.A. (2017, January 20\u201322). y Communication-Efficient Learning of Deep Networks from Decentralized Data. Proceedings of the 20th International Conference on Artificial Intelligence and Statistics, Fort Lauderdale, FL, USA."},{"key":"ref_26","doi-asserted-by":"crossref","unstructured":"Cao, X., Fang, M., Liu, J., and Gong, N.Z. (2021, January 21\u201325). FLTrust: Byzantine-Robust Federated Learning via Trust Bootstrapping. Proceedings of the Network and Distributed Systems Security (NDSS) Symposium 2021, Virtual.","DOI":"10.14722\/ndss.2021.24434"}],"container-title":["Computers"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/www.mdpi.com\/2073-431X\/15\/2\/121\/pdf","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,2,11]],"date-time":"2026-02-11T17:52:57Z","timestamp":1770832377000},"score":1,"resource":{"primary":{"URL":"https:\/\/www.mdpi.com\/2073-431X\/15\/2\/121"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,2,11]]},"references-count":26,"journal-issue":{"issue":"2","published-online":{"date-parts":[[2026,2]]}},"alternative-id":["computers15020121"],"URL":"https:\/\/doi.org\/10.3390\/computers15020121","relation":{},"ISSN":["2073-431X"],"issn-type":[{"value":"2073-431X","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026,2,11]]}}}