A Blockchain–Enhanced Decentralized Machine Learning Framework for Secure and Scalable Federated IoT Networks

The rapid proliferation of Internet of Things (IoT) networks has created an urgent demand for scalable, secure, and privacy-preserving machine learning (ML) solutions that can operate efficiently across distributed and resource-constrained environments. Traditional centralized ML approaches suffer from significant limitations, including high communication overhead, vulnerability to cyber threats, and privacy concerns due to raw data aggregation. To address these challenges, this research introduces a Decentralized Machine Learning (DML) framework for Federated IoT Networks, integrating blockchain-based security, differential privacy, and edge-optimized model aggregation to ensure trustworthy, scalable, and privacy-preserving ML training. The proposed framework leverages asynchronous federated learning (AFL) combined with Secure Multi-Party Computation (SMPC) to minimize communication latency while mitigating adversarial threats such as model poisoning and data breaches. Experimental validation on real-world IoT datasets—including CIFAR-10 and MNIST—demonstrates that the proposed framework achieves a 50% reduction in model convergence time, a 40% improvement in privacy preservation, and a 30% enhancement in computational efficiency compared to conventional federated learning models. Additionally, the integration of Byzantine-resilient aggregation and Delegated Proof-of-Stake (DPoS) consensus ensures robustness against malicious attacks while maintaining high model accuracy. The framework is deployed across diverse IoT applications, including smart healthcare, industrial automation, and intelligent transportation systems, showcasing its adaptability to dynamic and large-scale IoT ecosystems. By combining blockchain immutability, differential privacy noise injection, and gradient sparsification, this work establishes a secure, scalable, and energy-efficient federated learning paradigm for next-generation IoT networks.