Special Issue on Blockchain and Federated Learning for Secure and Privacy-Preserving Computing in Next-Generation IoT Systems, SN Computer Science.
About this Special Issue
The rapid proliferation of Internet of Things devices across healthcare, transportation, industrial, and smart city domains has created unprecedented challenges in securing distributed data and preserving user privacy. Conventional centralized security architectures struggle to cope with the scale, heterogeneity, and real-time demands of next-generation IoT systems, creating an urgent need for decentralized and intelligent security paradigms. Blockchain and federated learning have emerged as two transformative technologies that, individually and in combination, offer powerful solutions for secure, privacy-preserving, and trustworthy computing in distributed IoT environments. Blockchain provides decentralized trust, immutable record-keeping, and tamper-resistant authentication that eliminate single points of failure in IoT networks, enabling secure data sharing, verifiable transactions, and transparent access control. Federated learning enables collaborative model training across distributed IoT devices without exposing raw data, preserving privacy while supporting intelligent decision-making at the network edge. The integration of these technologies addresses critical concerns including data confidentiality, authentication, secure aggregation, and resistance to adversarial attacks in resource-constrained IoT settings.
This special issue focuses on the convergence of blockchain and federated learning to advance secure and privacy-preserving computing in next-generation IoT systems. Contributions are invited that explore novel architectures, lightweight cryptographic protocols, decentralized authentication frameworks, privacy-preserving aggregation mechanisms, and intelligent threat detection approaches. Research addressing scalability, energy efficiency, communication overhead, and real-world deployment across vehicular networks, healthcare systems, industrial IoT, and smart cities is strongly encouraged. By bringing together advances in decentralized security, collaborative intelligence, and privacy preservation, this special issue aims to provide a comprehensive understanding of how blockchain and federated learning can jointly secure the future of connected systems, offering both theoretical foundations and practical frameworks for building trustworthy, scalable, and privacy-aware IoT ecosystems. Potential topics included, but not limited:
- Blockchain-based decentralized authentication and access control for next-generation IoT systems
- Privacy-preserving federated learning frameworks for secure collaborative intelligence in distributed IoT networks
- Integration of blockchain and federated learning for secure data sharing and model aggregation in edge computing
- Lightweight cryptographic protocols for blockchain-enabled IoT in resource-constrained environments
- Secure and privacy-preserving federated learning for healthcare IoT and medical cyber-physical systems
- Blockchain and federated learning for trust management and threat detection in vehicular and industrial IoT networks
- Scalable and energy-efficient blockchain-federated learning architectures for smart city and 6G-enabled IoT applications
The submission deadline for this collection is 28 April 2027.
Guest Editors:
- George Drosatos
Athena Research Center, Greece - Pavlos Papadopoulos
Edinburgh Napier University, United Kingdom - Pandi Vijayakumar
J.J. College of Engineering and Technology, India
This Special Issue is provided by the journal "SN Computer Science" and more details are available here.