Abstract—The rapid growth of the Internet of Things (IoT), has created many security and privacy challenges. The large amount of data collected and exchanged by IoT devices increases their vulnerability to cyberattacks. Traditional security methods, like Role-Based Access Control (RBAC) has several limitations including single points of failure, poor scalability, and privacy risks caused by sending user data to centralized servers. To enhance security and privacy in the IoT environments, this paper proposes an integrated security framework which combines Zero Trust Security (ZTS), Blockchain-Based Access Control (BBAC), and Federated Learning (FL). Federated learning enables IoT devices to train Artificial Intelligence (AI) models locally without sending sensitive data to a central server to protect user privacy. BBAC verifies user identities through smart contracts and records all access requests in a decentralized ledger securely. ZTS grants access only after continuously monitoring and verifying their identity and behavior of users and devices. The proposed framework combines these three technologies into a single security solution for IoT environments. Federated learning supports intelligent and dynamic decision-making for Zero Trust authentication, while blockchain provides secure and decentralized access control. This integrated framework improves scalability, security, and user privacy compared with existing methods. Simulation results shows that the proposed framework successfully blocks up to 97.2% of cyberattacks and 98.5% of unauthorized access attempts. In addition, the blockchain network achieves a throughput of 120 transactions per second, demonstrating the effectiveness and efficiency of the proposed approach.
 
Keywords—Internet of Things (IoT), Federated Learning (FL), blockchain, cyber-attacks, security, edge Artificial Intelligence (AI)
 
Copyright © 2026 by the authors. This is an open access article distributed under the Creative Commons Attribution License which permits unrestricted use, distribution, and reproduction in any medium, provided the original work is properly cited (CC BY 4.0).