Blockchain-Enabled Federated Learning for Privacy-Preserving Cryptocurrency Fraud Detection

DOI

10.2991/978-94-6239-713-2_18How to use a DOI?

Keywords

Federated learning; Blockchain; Differential privacy; Cryptocurrency Fraud Detection; Data security; Ethereum

Abstract

The growth of cryptocurrency and decentralized financial systems has been very rapid, which has also increased the risk of fraudulent transactions. Traditional fraud detection techniques are usually based on centralized data collection, which raises serious concerns about data privacy, data security, and single points of failure. To address these challenges, this paper proposes a Blockchain-Enabled Federated Learning (BCFL) framework for privacy-preserving cryptocurrency fraud identification. The proposed approach enables a joint training of a global fraud detection model between multiple financial institutions or cryptocurrency exchanges without sharing their sensitive transaction information, Federated learning allows decentralized temperature (adding controlled noise to shared model updates, this method is known as Differential Privacy) model training In addition, a layer of the blockchain based on Ethereum smart contracts are used to record ensure unmodifiable and transparent logging of model updates and trainings to keep participating nodes accountable and transparent. Experimental evaluation takes place in a simulated multi-node environment to demonstrate that the proposed BCFL framework achieves high fraud detection accuracy, low false-positive and false-negative rates, and a low backoff factor. Strong privacy guarantees. The results show that the integration of federated learning, differential privacy, and blockchain technology provides a secure and transparent solution for fraud detection in modern decentralized financial ecosystems.

Copyright

© 2026 The Author(s)

Open Access

Open Access This chapter is licensed under the terms of the Creative Commons Attribution-NonCommercial 4.0 International License (http://creativecommons.org/licenses/by-nc/4.0/), which permits any noncommercial use, sharing, adaptation, distribution and reproduction in any medium or format, as long as you give appropriate credit to the original author(s) and the source, provide a link to the Creative Commons license and indicate if changes were made.

Download article (PDF)

TY  - CONF
AU  - Ramesh Eri
AU  - Vijaya Lakshmi Thalari
AU  - Sravanthi Reddy Vulavbeeti
AU  - Tejaswini Yatham
AU  - Veena Sree Venkata
PY  - 2026
DA  - 2026/06/25
TI  - Blockchain-Enabled Federated Learning for Privacy-Preserving Cryptocurrency Fraud Detection
BT  - Proceedings of the International Conference on Advances in Computing Technology and Artificial Intelligence (COMPUTATIA 2026)
PB  - Atlantis Press
SP  - 245
EP  - 254
SN  - 2589-4919
UR  - https://doi.org/10.2991/978-94-6239-713-2_18
DO  - 10.2991/978-94-6239-713-2_18
ID  - Eri2026
ER  -