Privacy-Preserving COVID-19 Data Analysis

Overview

A differential privacy implementation for analyzing COVID-19 patient data while protecting sensitive information.

This project leverages Differential Privacy (DP) techniques to analyze and predict COVID-19 patient risks using a large-scale dataset. By incorporating algorithms such as Gaussian Noise, Report Noisy Max, and the Exponential Mechanism, we ensure the protection of sensitive patient information while providing meaningful insights. This project addresses the critical need for privacy-preserving data analysis in healthcare, balancing privacy with actionable utility.

Features

• Implementation of multiple differential privacy algorithms (Gaussian Noise, Report Noisy Max, Exponential Mechanism)
• Analysis of COVID-19 patient data with privacy guarantees
• Risk prediction while maintaining patient confidentiality
• Balance between data utility and privacy protection
• Interactive visualization of privacy-preserved data analysis
• Configurable privacy parameters to adjust the privacy-utility tradeoff