EUVIMEDEUVIMED entdecken
Open Access · CC BY-NC-ND 4.0

Federated Learning Ensemble Voting-Based Methods to Deal with Non-IID and Imbalanced Data in Cybersecurity

Bruno H. Meyer, Michele Nogueira, Wagner M. Nunan Zola, Aurora Pozo

ADCAIJ: Advances in Distributed Computing and Artificial Intelligence Journal · 24.03.2026 · 14 · e32905

DOI: 10.14201/adcaij.32905 ↗

Kurz gefasst

Fachartikel in der Zeitschrift ADCAIJ: Advances in Distributed Computing and Artificial Intelligence Journal, online erschienen am 24.03.2026. Verfasst von Bruno H. Meyer und 3 weiteren Autor:innen. Die Arbeit nennt 37 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY-NC-ND 4.0).

AbstractBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Cybersecurity is an essential topic in society due to the increasing application of technology across different application industries that are connected to the Internet. There are several methods to address cybersecurity challenges, such as Intrusion Detection Systems (IDS). This article presents new methods based on Federated Learning that can be applied to IDS to improve cybersecurity attack detection. Researchers use different approaches to create IDS solutions, including machine learning algorithms and techniques such as Federated Learning (FL) to classify network traffic as normal or malicious. FL is an emerging technology and is expected to benefit cybersecurity by improving attack detection and threat identification. It consists of a set of clients, each one with local data, whose goal is to collaboratively train one or more global models without centralizing the data, through several iterations known as rounds. An important characteristic to consider in cybersecurity data for machine learning algorithms is the presence of non-Independent and Identically Distributed (non-IID) and imbalanced data. Non-IID data describes FL datasets in which data is not evenly distributed between clients. Unlike previously proposed methods in other works, this article proposes approaches that focus on non-IID data while using FL to create models without requiring multiple training rounds. The FLENV and FLEWNV methods are proposed, implementing a federated learning framework that uses a single training round and aggregates clients through ensemble learning with normalized and weighted voting, focusing on non-IID and imbalanced data. The well-known Ton-IoT and Bot-IoT datasets were analyzed to evaluate the proposed methods and other possibilities commonly used in the state of the art. The approaches outperformed other methods from the literature in the experiments, indicating that leveraging knowledge of non-IID and imbalanced data in cybersecurity can lead to improved attack classification frameworks.

Zitieren

APA

Meyer, B. H., Nogueira, M., Zola, W. M. N., & Pozo, A. (2026). Federated Learning Ensemble Voting-Based Methods to Deal with Non-IID and Imbalanced Data in Cybersecurity. ADCAIJ: Advances in Distributed Computing and Artificial Intelligence Journal, 14, e32905. https://doi.org/10.14201/adcaij.32905

Vancouver

Meyer BH, Nogueira M, Zola WMN, Pozo A. Federated Learning Ensemble Voting-Based Methods to Deal with Non-IID and Imbalanced Data in Cybersecurity. ADCAIJ: Advances in Distributed Computing and Artificial Intelligence Journal. 2026;14:e32905. doi:10.14201/adcaij.32905

BibTeX
@article{Meyer2026,
  author = {Meyer, Bruno H. and Nogueira, Michele and Zola, Wagner M. Nunan and Pozo, Aurora},
  title = {Federated Learning Ensemble Voting-Based Methods to Deal with Non-IID and Imbalanced Data in Cybersecurity},
  journal = {ADCAIJ: Advances in Distributed Computing and Artificial Intelligence Journal},
  year = {2026},
  volume = {14},
  pages = {e32905},
  doi = {10.14201/adcaij.32905}
}
Kostenlos starten →