EUVIMEDEUVIMED entdecken
Open Access · CC BY 4.0

A Triad of Defenses to Mitigate Poisoning Attacks in Federated Learning

Blenda Oliveira Mazetto, Bruno Bogaz Zarpelão

Journal of the Brazilian Computer Society · 16.03.2026 · 32 (1) · 316-331

DOI: 10.5753/jbcs.2026.5558 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Journal of the Brazilian Computer Society, online erschienen am 16.03.2026. Verfasst von Blenda Oliveira Mazetto und 1 weiteren Autor:innen. Die Arbeit wurde bisher 1-mal zitiert (Crossref) und nennt 24 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0).

AbstractBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Federated learning (FL) enables the training of machine learning models on decentralized data, potentially improving data privacy. However, the FL distributed architecture is vulnerable to poisoning attacks. In this paper, we propose an FL method capable of mitigating these attacks through a triad of defense strategies: organizing clients into groups, evaluating the local performance of global models during training, and using a voting scheme during the inference phase. The proposed approach first divides the clients into randomly sampled groups, each generating a distinct global model. Each client trains a local model on their private data and submits it to the central server. The central server aggregates the local models within each group to generate the global models. Then, each client receives all global models, selects the best performing one as their new local model, and the process repeats until training is complete. During the inference phase, each client classifies its inputs according to a majority-based voting scheme among the global models. Our experiments using the HAR and MNIST datasets demonstrate that our method can effectively mitigate poisoning attacks without compromising the global model's performance.

Zitieren

APA

Mazetto, B. O., & Zarpelão, B. B. (2026). A Triad of Defenses to Mitigate Poisoning Attacks in Federated Learning. Journal of the Brazilian Computer Society, 32(1), 316-331. https://doi.org/10.5753/jbcs.2026.5558

Vancouver

Mazetto BO, Zarpelão BB. A Triad of Defenses to Mitigate Poisoning Attacks in Federated Learning. Journal of the Brazilian Computer Society. 2026;32(1):316-331. doi:10.5753/jbcs.2026.5558

BibTeX
@article{Mazetto2026,
  author = {Mazetto, Blenda Oliveira and Zarpelão, Bruno Bogaz},
  title = {A Triad of Defenses to Mitigate Poisoning Attacks in Federated Learning},
  journal = {Journal of the Brazilian Computer Society},
  year = {2026},
  volume = {32},
  number = {1},
  pages = {316--331},
  doi = {10.5753/jbcs.2026.5558}
}
Kostenlos starten →