Related Experiment Videos
Blockchain-enhanced federated learning for IoT security and privacy using the GSR-C2N model.
Shahnawaz Ahmad1, Mohd Aquib Ansari2, Arvind Mewada1
1School of Computer Science Engineering and Technology, Bennett University, Greater Noida, 201310, India.
Scientific Reports
|June 10, 2026
Summary
This study introduces a federated learning (FL) framework with blockchain to secure Internet of Things (IoT) devices against crypto-mining malware. The integrated system enhances privacy and trust for scalable, secure machine learning applications.
Area of Science:
- Cybersecurity
- Machine Learning
- Blockchain Technology
Background:
- The proliferation of Internet of Things (IoT) devices necessitates advanced security and privacy-preserving machine learning solutions.
- Federated Learning (FL) enables decentralized model training without raw data transfer, while blockchain offers trust and transparency.
- Existing security measures struggle to keep pace with the evolving threats in interconnected IoT environments.
Purpose of the Study:
- To develop and evaluate a novel Federated Learning (FL) framework integrated with blockchain technology.
- To enhance the security, privacy, and scalability of machine learning models for IoT devices.
- To specifically address the threat of crypto-mining malware in IoT ecosystems using a GSR-C2N model.
Main Methods:
- Implementation of a Federated Learning (FL) framework incorporating blockchain for decentralized model training.
- Utilizing blockchain to verify model updates, ensuring integrity and consensus among distributed IoT devices.
- Employing the GSR-C2N model for feature extraction and optimization tailored for crypto-mining malware identification.
Main Results:
- The proposed FL-blockchain framework demonstrated superior performance compared to current practices in IoT security.
- The model achieved 96.85% accuracy and 97.51% specificity on a crypto-mining malware dataset via 10-fold cross-validation.
- Blockchain integration effectively enhanced trust and privacy by verifying model updates and optimizing feature extraction.
Conclusions:
- The developed FL-blockchain framework offers a robust solution for securing IoT systems against sophisticated cyber threats like crypto-mining malware.
- The model's high accuracy and specificity indicate its applicability in critical IoT domains such as smart healthcare and smart cities.
- Combining the framework with homomorphic encryption and regulatory compliance further strengthens data privacy management in advanced IoT applications.
