Arshad, Usama, Tubaishat, Abdallah, Alarfaj, Fawaz, Halim, Zahid, Anwar, Sajid, Alfuhaid, Hisham and Waqas, Muhammad ORCID: https://orcid.org/0000-0003-0814-7544 (2026) Zero-trust privacy enforcement and threat-awarer monitoring in consumer healthcare systems. IEEE Transactions on Consumer Electronics. ISSN 0098-3063 (Print), 1558-4127 (Online) (doi:10.1109/TCE.2026.3723896)

Preview

PDF (Author's Accepted Manuscript) 54031 WAQAS_Zero-trust_Privacy_Enforcement_(AAM)_2026.pdf - Accepted Version Available under License Creative Commons Attribution. Download (3MB) | Preview

Abstract

Consumer healthcare applications increasingly rely on AI-driven monitoring, IoMT devices, and continuous data collection, creating critical challenges involving privacy, unauthorized access, excessive surveillance, and secure healthcaredata management. This paper proposes a zero-trust, threataware architecture that integrates context-aware computer vision, blockchain-based decentralized access control, and zero-knowledge proofs for privacy-preserving healthcare monitoring. The framework filters incoming streams to retain only healthcare-relevant events; encrypted records remain off-chain, whereas hashes, access decisions, consent states, and audit logs are recorded on a consortium blockchain. Zero-knowledge proofs support confidential authorization, whereas reputation-aware trust management and blockchain-enabled incentives promote reliable participation and discourage malicious behavior. Clinical events, including falls and abnormal postures, are detected through a CNN-LSTM model, while cybersecurity threats are identified through policy evaluation, transaction validation, and behavioral monitoring. Across 30 independent runs under varied workloads and attack conditions, the proposed architecture achieved a 54.5% reduction in data-access time, a 52.4% reduction in breach-response time, and a 78.1% reduction in privacy and integrity incidents compared with a conventional architecture. Simulated participation increased by 43.7% after incentive deployment across 12 monthly scenarios. These results indicate improved efficiency, privacy preservation, and threat responsiveness for AI-enabled consumer healthcare monitoring.

Item Type:	Article
Additional Information:	The Author's Accepted Manuscript is covered by the IEEE IEL Read-only plus green open access arrangement 2025-2027.
Uncontrolled Keywords:	computer vision, zero-trust security, blockchain, zero-knowledge proofs, healthcare monitoring, privacy preservation
Subjects:	Q Science > Q Science (General) Q Science > QA Mathematics > QA75 Electronic computers. Computer science
Faculty / School / Research Centre / Research Group:	Faculty of Engineering & Science Faculty of Engineering & Science > School of Computing & Mathematical Sciences (CMS)
Last Modified:	17 Aug 2026 16:15
URI:	https://gala.gre.ac.uk/id/eprint/54031

Actions (login required)

View Item

Downloads