AI-Based Infectious-Disease Surveillance Monitoring Using Koipe Mechanism

In today's interconnected world, individuals' health and location data are often dispersed across multiple organizations, holding the potential to yield valuable insights when consolidated and analyzed. However, merging data from various hosting sites poses significant privacy risks, even when employing security measures. This project delves into a novel data-analytics platform designed to identify infectious disease geographic hotspots by combining and examining users' location and health data, housed separately in two distinct cloud environments. A core focus of the study is to evaluate the privacy implications of this platform employs a technology known as key-oblivious inner product encryption (KOIPE) mechanism. This encryption method ensures that only aggregated statistical data is disclosed to potential snooping entities, termed as honest-but-curious (HbC) entities. To fortify user confidentiality against potential inference attacks, a game-theoretic strategy is employed. This approach incentivizes consumers to collaboratively build anonymous clusters that support quantified privacy assurance. By addressing the intricate balance between data integration and privacy preservation, this project aims to pioneer a secure and privacy-centric approach to infectious disease surveillance. Through rigorous analysis and innovative methodologies, the platform seeks to empower public health authorities with actionable insights while safeguarding individual privacy rights, fostering trust, and promoting user engagement in health-related data sharing and analytics.