Blockchain-Assisted Federated Learning for Cybersecurity: Combining Isolation Forest, Variational Autoencoders, and Differential Privacy

Authors

  • Durga Praveen Devi
  • Naga Sushma Allur
  • Koteswararao Dondapati
  • Himabindu Chetlapalli
  • Sharadha Kodadi
  • Aravindhan Kurunthachalam

DOI:

https://doi.org/10.46243/jst.2025.v10.i02.pp95-107

Keywords:

Blockchain, Federated Learning,, Anomaly Detection,, Differential Privacy,, Cybersecurity, Isolation Forest,, Variational Autoencoders

Abstract

The complexity of the cyber threats dictates the need for strong, privacy-preserving
mechanisms for anomaly detection. This paper introduces a new framework called BAFL, an
integration of Isolation Forest and Variational Autoencoders combined with Differential
Privacy, for safe and scalable solutions in cybersecurity applications. Federated Learning
allows distributed training across numerous clients without exposure of sensitive information,
while the blockchain technology introduces trust and integrity in model updates.

Downloads

Published

2025-02-28

How to Cite

Durga Praveen Devi, Naga Sushma Allur, Koteswararao Dondapati, Himabindu Chetlapalli, Sharadha Kodadi, & Aravindhan Kurunthachalam. (2025). Blockchain-Assisted Federated Learning for Cybersecurity: Combining Isolation Forest, Variational Autoencoders, and Differential Privacy. Journal of Science & Technology (JST), 10(2), 95–107. https://doi.org/10.46243/jst.2025.v10.i02.pp95-107