Federated Learning and Blockchain Framework for Scalable and Secure IoT Access Control

The increasing deployment of Internet of Things (IoT) devices has introduced significant security challenges, including identity spoofing, unauthorized access, and data integrity breaches. Traditional security mechanisms rely on centralized frameworks that suffer from single points of failure, scalability issues, and inefficiencies in real-time security enforcement. To address these limitations, this study proposes the Blockchain-Enhanced Trust and Access Control for IoT Security (BETAC-IoT) model, which integrates blockchain technology, smart contracts, federated learning, and Merkle tree-based integrity verification to enhance IoT security. The proposed model eliminates reliance on centralized authentication by employing decentralized identity management, ensuring tamper-proof data storage, and automating access control through smart contracts. Experimental evaluation using a synthetic IoT dataset shows that the BETAC-IoT model improves access control enforcement accuracy by 92%, reduces device authentication time by 52% (from 2.5 to 1.2 s), and enhances threat detection efficiency by 7% (from 85% to 92%) using federated learning. Additionally, the hybrid blockchain architecture achieves a 300% increase in transaction throughput when comparing private blockchain performance (1200 TPS) to public chains (300 TPS). Access control enforcement accuracy was quantified through confusion matrix analysis, with high precision and minimal false positives observed across access decision categories. Although the model presents advantages in security and scalability, challenges such as computational overhead, blockchain storage constraints, and interoperability with existing IoT systems remain areas for future research. This study contributes to advancing decentralized security frameworks for IoT, providing a resilient and scalable solution for securing connected environments.