Blockchain-based zero trust networks with federated transfer learning for IoT security in industry 5.0

Ankita Sharma, Shalli Rani and Wadii Boulila

PLOS ONE, 2025, vol. 20, issue 6, 1-16

Abstract: The rise of Industry 5.0 focuses on merging advanced intelligence, automation, and human-centered teamwork in industrial settings. However, keeping interconnected IoT networks secure is still a challenging problem. This paper proposes a new security framework that combines Blockchain, Federated Transfer Learning, and zero trust network (ZTN) principles to improve IoT security in Industry 5.0. Blockchain is a decentralized ledger that ensures secure data sharing and protects model updates. Federated Transfer Learning allows model training across distributed IoT devices to keep data private. The ZTN approach enforces strict access rules, assuming that no entity is trusted by default. The proposed framework offers a scalable and resilient solution to protect next-generation industrial IoT networks, using Blockchain for data security, transfer learning for adaptability, and ZTN for strict access control. The ZTN architecture strengthens security by checking every access request and keeping the IoT system safe. The experimental results show good performance of the proposed method, with better accuracy, precision, recall, and F1 scores. The model achieved an accuracy of 0.85, 0.88, and 0.87 for learning rates of 0.01, 0.001, and 0.0001, respectively, at 100 epochs. The precision values reached 0.84, 0.87, and 0.86, while the recall scores were 0.82, 0.86, and 0.85, respectively. The F1-scores were recorded at 0.83, 0.86, and 0.85, which confirms the robustness of our model.

Date: 2025
References: View references in EconPapers View complete reference list from CitEc
Citations:

Downloads: (external link)
https://journals.plos.org/plosone/article?id=10.1371/journal.pone.0323241 (text/html)
https://journals.plos.org/plosone/article/file?id= ... 23241&type=printable (application/pdf)

Related works:
This item may be available elsewhere in EconPapers: Search for items with the same title.

Export reference: BibTeX RIS (EndNote, ProCite, RefMan) HTML/Text

Persistent link: https://EconPapers.repec.org/RePEc:plo:pone00:0323241

DOI: 10.1371/journal.pone.0323241

Access Statistics for this article

More articles in PLOS ONE from Public Library of Science
Bibliographic data for series maintained by plosone ().