AI Lap Lambert Academic Publishing AI Enhanced Blockchain Security for IoT Networks

The rapid expansion of IoT and cloud-enabled wireless systems has created significant security challenges, particularly for resource-constrained devices with limited energy, computational capacity, and network resources. These constraints make IoT nodes highly susceptible to cyber threats, including Distributed Denial-of-Service (DDoS) attacks, Sybil attacks, packet tampering, data manipulation, and unauthorized access. To address these challenges, this research proposes an intelligent and integrated security framework that combines machine learning-based anomaly detection, blockchain-enabled authentication, and bio-inspired optimization techniques to enhance security, trustworthiness, scalability, and overall network performance. The framework utilizes supervised multiclass and one-class machine learning classifiers to identify both known and previously unseen anomalies in near real time using measurable network and communication parameters. To ensure data integrity, transparency, and decentralized trust management, a blockchain architecture incorporating a novel Proof of Iterative Trust (PoIT) consensus mechanism is employed. Furthermore, cloud-scale efficiency is improved.