Robustness-Enhanced and Explainable Federated Learning in Internet of Things
IEEE Internet of Things Journal · 01.06.2026 · 13 (11) · 24261-24272
DOI: 10.1109/jiot.2026.3672451 ↗Kurz gefasst
Fachartikel in der Zeitschrift IEEE Internet of Things Journal, erschienen am 01.06.2026. Verfasst von Shuying Liu und 10 weiteren Autor:innen. Die Arbeit nennt 41 Literaturangaben. Gefördert von: College Students’ Innovation and Entrepreneurship Training Program, Natural Science Basic Research Plan in Shaanxi Province of China, National Natural Science Foundation of China.
Abstract (Originalsprache)
In the Internet of Things (IoT) environment, a large number of edge devices collaboratively generate and process data, making federated learning (FL) an appealing solution for privacy-preserving model training without sharing raw data. However, traditional FL frameworks suffer from performance degradation due to model poisoning attacks under nonindependent and identically distributed (non-IID) settings, as well as a lack of decision-making explainability. To address these challenges, we propose the robustness-enhanced and explainable federated learning (ReFed) framework by combining local interpretable model-agnostic explanations (LIME) with similarity-based aggregation. Specifically, by fitting a local linear regression model to approximate the decision processes of both the global and local models for improved transparency and dynamically computing client aggregation weights based on intermodel prediction similarity for enhanced robustness. Experiments demonstrate that ReFed achieves 99.76% accuracy on MNIST and 87.65% accuracy on CIFAR-10, outperforming typical FL methods in adversarial settings.
Förderung
- College Students’ Innovation and Entrepreneurship Training Program
- Natural Science Basic Research Plan in Shaanxi Province of China
- National Natural Science Foundation of China
- Cloud Technology Endowed Professorship
Zitieren
APA
Liu, S., Tian, J., Meng, R., Zhang, Y., Miao, Y., Liu, Z., Peng, J., Zou, Y., Wang, Z., Li, H., & Choo, K. R. (2026). Robustness-Enhanced and Explainable Federated Learning in Internet of Things. IEEE Internet of Things Journal, 13(11), 24261-24272. https://doi.org/10.1109/jiot.2026.3672451
Vancouver
Liu S, Tian J, Meng R, Zhang Y, Miao Y, Liu Z, et al. Robustness-Enhanced and Explainable Federated Learning in Internet of Things. IEEE Internet of Things Journal. 2026;13(11):24261-24272. doi:10.1109/jiot.2026.3672451
BibTeX
@article{Liu2026,
author = {Liu, Shuying and Tian, Jiameng and Meng, Ru and Zhang, Yifan and Miao, Yinbin and Liu, Zhiquan and Peng, Jinye and Zou, Yanfei and Wang, Zheben and Li, Hong and Choo, Kim-Kwang Raymond},
title = {Robustness-Enhanced and Explainable Federated Learning in Internet of Things},
journal = {IEEE Internet of Things Journal},
year = {2026},
volume = {13},
number = {11},
pages = {24261--24272},
doi = {10.1109/jiot.2026.3672451}
}
EUVIMED