EUVIMEDEUVIMED entdecken
Crossref

Privacy-Preserving Email Spam Detection using Federated Learning

Roshni M, Thangadurai K

International Journal of Engineering & Extended Technologies Research · 28.03.2026 · 08 (02)

DOI: 10.15662/ijeetr.2026.0802029 ↗

Kurz gefasst

Fachartikel in der Zeitschrift International Journal of Engineering & Extended Technologies Research, online erschienen am 28.03.2026. Verfasst von Roshni M und 1 weiteren Autor:innen.

AbstractBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

The rapid growth of electronic communication has led to an increased prevalence of email spam, posing significant challenges to user privacy and cybersecurity. Traditional centralized spam detection approaches require collecting large volumes of user data on central servers, raising serious privacy concerns and regulatory issues. To address these challenges, this study proposes a privacy-preserving email spam detection framework based on federated learning. The proposed method enables multiple clients to collaboratively train a global machine learning model without sharing raw email data, thereby ensuring data confidentiality. In this approach, local models are trained on decentralized datasets residing on user devices, and only model updates are transmitted to a central server for aggregation. To further enhance privacy, techniques such as secure aggregation and differential privacy are incorporated to prevent leakage of sensitive information from model parameters. The system employs natural language processing techniques for feature extraction and utilizes classification algorithms to distinguish between spam and legitimate emails. Experimental results demonstrate that the federated learning-based model achieves competitive accuracy compared to traditional centralized methods while significantly reducing privacy risks. Additionally, the framework shows robustness against data heterogeneity and scalability across multiple clients. The proposed solution highlights the potential of federated learning as an effective and privacy-aware paradigm for real-world spam detection systems.

Zitieren

APA

M, R., & K, T. (2026). Privacy-Preserving Email Spam Detection using Federated Learning. International Journal of Engineering & Extended Technologies Research, 08(02). https://doi.org/10.15662/ijeetr.2026.0802029

Vancouver

M R, K T. Privacy-Preserving Email Spam Detection using Federated Learning. International Journal of Engineering & Extended Technologies Research. 2026;08(02). doi:10.15662/ijeetr.2026.0802029

BibTeX
@article{M2026,
  author = {M, Roshni and K, Thangadurai},
  title = {Privacy-Preserving Email Spam Detection using Federated Learning},
  journal = {International Journal of Engineering & Extended Technologies Research},
  year = {2026},
  volume = {08},
  number = {02},
  doi = {10.15662/ijeetr.2026.0802029}
}
Kostenlos starten →