AI-Driven, Privacy-Preserving Contact Tracing and Pandemic Response Systems. . .
Abstract
The COVID-19 pandemic exposed fundamental weaknesses in traditional contact-tracing and data-sharing systems, where centralized architectures often compromised user privacy and response speed.
This paper proposes a federated learning-based contact-tracing framework integrated with zero-trust network architecture (ZTNA) to achieve secure, privacy-preserving, and scalable public-health monitoring.
The system leverages decentralized model training on user devices, enabling anonymized data aggregation and real-time threat detection without exposing sensitive personal information.
Experimental simulations demonstrate that the approach enhances outbreak response accuracy by 28 % while maintaining strict data confidentiality, making it a viable model for future pandemic management and critical health-security applications.
This paper proposes a federated learning-based contact-tracing framework integrated with zero-trust network architecture (ZTNA) to achieve secure, privacy-preserving, and scalable public-health monitoring.
The system leverages decentralized model training on user devices, enabling anonymized data aggregation and real-time threat detection without exposing sensitive personal information.
Experimental simulations demonstrate that the approach enhances outbreak response accuracy by 28 % while maintaining strict data confidentiality, making it a viable model for future pandemic management and critical health-security applications.
Type
Publication
International Journal of Engineering and Technical Research (IJETR)
This research introduces a federated learning and zero-trust security model for real-time pandemic response.
It ensures privacy, scalability, and data integrity across distributed health networks.
