Copyright © 2026 Authors retain the copyright of this article. This article 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.

@article{204976,
        author = {Nimisha Boban and Sreenandhana C S and Anil M},
        title = {GUIDEDVERIFED: SECURE FEDERATED LEARNING FOR INDUSTRIAL IOT},
        journal = {International Journal of Innovative Research in Technology},
        year = {2026},
        volume = {13},
        number = {1},
        pages = {5077-5080},
        issn = {2349-6002},
        url = {https://ijirt.org/article?manuscript=204976},
        abstract = {With the rapid expansion of Industrial Internet of Things (IIoT) systems, ensuring data privacy, trust, and secure analytics has become a critical challenge. Traditional centralized machine learning approaches require raw data sharing, which introduces privacy risks and vulnerability to tampering. This project presents GuidedVeriFed, a secure multi-layered framework that integrates Federated Learning (FL), Differential Privacy, Blockchain, and Digital Twin technology to address these concerns. Federated Learning enables local model training at IIoT devices, eliminating raw data transfer and thereby achieving complete data confidentiality. Differential Privacy is applied to model updates to prevent leakage of sensitive information while maintaining high model accuracy above 95 percentage. Blockchain technology is employed to securely log model updates, ensuring integrity, traceability, and resistance to tampering. A Digital Twin model replicates real-time IIoT operations to verify system behavior and detect anomalies proactively. The combined framework significantly improves privacy preservation, trustworthiness, and anomaly detection capabilities in IIoT analytics. Experimental results demonstrate secure model collaboration, robust anomaly identification, and enhanced resilience against malicious attacks. The proposed solution provides a scalable, trustworthy, and privacy-preserving approach suitable for mod-ern industrial environments.},
        keywords = {},
        month = {June},
        }