EUVIMEDEUVIMED entdecken
Open Access · CC BY 4.0

Mean/Std: Lightweight Distribution-Aware Aggregation for Federated IoT Botnet Detection

Yassine El Yamani, Youssef Baddi, Najib El Kamoun

IoT · 07.07.2026 · 7 (3) · 55

DOI: 10.3390/iot7030055 ↗

Kurz gefasst

Fachartikel in der Zeitschrift IoT, online erschienen am 07.07.2026. Verfasst von Yassine El Yamani und 2 weiteren Autor:innen. Die Arbeit nennt 32 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0).

AbstractBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Federated learning (FL) is a promising paradigm for privacy-preserving IoT intrusion detection, but its effectiveness can be substantially degraded by the combination of heterogeneous non-IID client distributions and severe multi-class imbalance. Under such conditions, conventional size-based aggregation may overemphasize large yet highly skewed clients, limiting the representation of minority attack classes in the global model. To address this issue, we propose Mean/Std, a lightweight distribution-aware aggregation strategy that combines a client-size proxy with two complementary statistics of local label distributions, namely the standard deviation and the dominance gap of class proportions, while preserving a communication footprint comparable to FedAvg. Experiments on the N-BaIoT benchmark, comprising seven heterogeneous IoT clients and eleven traffic classes, are conducted under a privacy-oriented update-perturbation setting inspired by secure aggregation workflows. The results show that Mean/Std consistently provides the strongest imbalance-aware performance among the evaluated FL baselines, achieving a Macro-F1 score of 0.8418 and a Balanced Accuracy of 0.8722 while improving the representation of minority attack classes. Additional experiments across five independent random seeds and a comprehensive hyperparameter sensitivity analysis further confirm the robustness and stability of the proposed aggregation mechanism. Overall, the results demonstrate that lightweight distribution-aware aggregation offers an effective, robust, and practically deployable solution for mitigating aggregation bias under simultaneous non-IID heterogeneity and severe multi-class imbalance in FL-based IoT botnet detection.

Zitieren

APA

Yamani, Y. E., Baddi, Y., & Kamoun, N. E. (2026). Mean/Std: Lightweight Distribution-Aware Aggregation for Federated IoT Botnet Detection. IoT, 7(3), 55. https://doi.org/10.3390/iot7030055

Vancouver

Yamani YE, Baddi Y, Kamoun NE. Mean/Std: Lightweight Distribution-Aware Aggregation for Federated IoT Botnet Detection. IoT. 2026;7(3):55. doi:10.3390/iot7030055

BibTeX
@article{Yamani2026,
  author = {Yamani, Yassine El and Baddi, Youssef and Kamoun, Najib El},
  title = {Mean/Std: Lightweight Distribution-Aware Aggregation for Federated IoT Botnet Detection},
  journal = {IoT},
  year = {2026},
  volume = {7},
  number = {3},
  pages = {55},
  doi = {10.3390/iot7030055}
}
Kostenlos starten →