Federated Blockchain Learning: A Hybrid Privacy-Preserving Framework for Secure Data Analytics
Summary
No summary yet. VIRAT can read this paper and write a plain-language summary of its aim, methods, key findings and limitations.
Summarise with VIRAT Free to try with your Science Catalogs account.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.
Fields of Study & Subjects
Privacy-Preserving Technologies in Data
Blockchain Technology Applications and Security
Blockchain Technology in Education and Learning
Publication details
- Journal / source
- Advances in intelligent systems research/Advances in Intelligent Systems Research
- Pages
- 1415–1422
- Publication date
- 1 April 2026
- Language
- EN
- Document type
- Book chapter