article · Journal Of Big Data
Federated learning enables collaborative machine learning across distributed devices without sharing raw data. However, the architecture faces significant vulnerabilities, including model poisoning attacks, data integrity risks, reverse engineering, and substantial communication overheads. Integrating blockchain technology addresses these weaknesses by providing a decentralised foundation that enhances overall system security, reliability, and performance. Incorporating cryptographic techniques, tamper-proof data logging, and decentralised consensus protocols helps mitigate poisoning attacks while preserving model integrity and decreasing communication costs. The approach applies across horizontal, vertical, and transfer federated learning structures. Successful wider implementation requires further development in regulatory compliance, system interoperability, and lightweight consensus mechanisms capable of functioning within distributed networks while addressing ethical and privacy requirements.
Training artificial intelligence models across multiple organisations typically risks exposing sensitive underlying data or succumbing to malicious tampering. By combining federated learning with blockchain, systems can securely train models collaboratively without centralising raw data. This approach protects data integrity, defends against malicious attacks, and establishes accountability, enabling safer multi-party data collaboration across privacy-sensitive environments.
The reviewed technologies could enable secure, collaborative artificial intelligence applications for organisations needing to train models across distributed, sensitive datasets without pooling raw information. Because this work constitutes a literature review categorising existing frameworks, concepts, and challenges rather than presenting a tested product, the technology remains at an early stage of development. Practical commercial deployment will depend on creating lightweight consensus mechanisms and establishing clear frameworks for cross-system interoperability and regulatory compliance.
AI-generated from the published abstract. Always read the original work before citing.
Abstract Federated Learning (FL) is a promising form of distributed machine learning that preserves privacy by training models locally without sharing raw data. While FL ensures data privacy through collaborative learning, it faces several critical challenges. These include vulnerabilities to reverse engineering, risks to model architecture privacy, susceptibility to model poisoning attacks, threats to data integrity, and the high costs associated with communication and connectivity. This paper presents a comprehensive review of FL, categorizing data partitioning formats into horizontal federated learning, vertical federated learning, and federated transfer learning. Furthermore, it explores the integration of FL with blockchain, leveraging blockchain’s decentralized nature to enhance FL’s security, reliability, and performance. The study reviews existing FL models, identifying key challenges such as privacy risks, communication overhead, model poisoning vulnerabilities, and ethical dilemmas. It evaluates privacy-preserving mechanisms and security strategies in FL, particularly those enabled by blockchain, such as cryptographic methods, decentralized consensus protocols, and tamper-proof data logging. Additionally, the research analyzes regulatory and ethical considerations for adopting blockchain-based FL solutions. Key findings highlight the effectiveness of blockchain in addressing FL challenges, particularly in mitigating model poisoning, ensuring data integrity, and reducing communication costs. The paper concludes with future directions for integrating blockchain and FL, emphasizing areas such as interoperability, lightweight consensus mechanisms, and regulatory compliance.
This page summarises published work. The authoritative version sits with the publisher.
DOI: 10.1186/s40537-025-01099-5
Is something wrong with this record? Report it or request removal.
Discussion
Have you built on this work, tried to replicate it, or seen it applied in practice? Share what you know. Verified researchers and MARATTO™ domain experts can open a discussion, and any member can reply. Contributions are reviewed before they appear.
No discussion yet. Open the first thread.
New to MARATTO™? Create a free account.
