Federated Blockchain Learning: A Hybrid Privacy-Preserving Framework for Secure Data Analytics

DOI

10.2991/978-94-6239-616-6_103How to use a DOI?

Keywords

Federated learning; Blockchain; Privacy Preservation; Secure Data Analytics; Trustworthy

Abstract

In this datacentric world, almost all organizations produce prodigious amount of information that will be useful for artificial intelligence- based analytics. But, sharing sensitive data across all the organizations introduces challenges in privacy, security, and trust. This manuscript proposes a Federated Blockchain Learning (FBL) framework – a hybrid privacy-preserving model that can interconnect federated learning (FL) and blockchain technologies to allow secure, transparent, and decentralized data analytics. Federated learning enables scattered participants to unitedly train AI models without unveiling their raw(exact) data, meanwhile blockchain provides a distributed ledger which assures data immutability, traceability, and trust amongst the participants. This proposed framework provides a new paradigm for trustworthy AI, reducing the risk of data leakage. Simulation results and conceptual analysis denote that this hybrid system enhances both privacy and accuracy for secure data analytics applications. From the stimulation outcomes we can confirm that, the above stated federated blockchain model improves training accuracy by secure data aggregation, faster convergence and reduces communication delay simultaneously ensuring tamper-proof data exchange through blockchain integration.

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  - Aashika Murugadasan
PY  - 2026
DA  - 2026/03/31
TI  - Federated Blockchain Learning: A Hybrid Privacy-Preserving Framework for Secure Data Analytics
BT  - Proceedings of the International Conference on Artificial Intelligence and Secure Data Analytics (ICAISDA 2025)
PB  - Atlantis Press
SP  - 1415
EP  - 1422
SN  - 1951-6851
UR  - https://doi.org/10.2991/978-94-6239-616-6_103
DO  - 10.2991/978-94-6239-616-6_103
ID  - Murugadasan2026
ER  -