Between Privacy and Utility: Navigating Inference Risks in De-Identified Health Data

Swati Kar, Lokesh Chinthala, Akram Mohammed, Robert Davis, Shahnewaz Karim Sakib

Confirmation: I have read and agree with the IEEE BHI 2025 conference submission's policy on behalf of myself and my co-authors.

Keywords: Precision Health, Inference Attack, Differential Privacy, Privacy-Preserving Machine Learning, AI-Driven Health Analytics

TL;DR: The paper investigates the vulnerability of de-identified healthcare data to inference attacks and shows how applying differential privacy with varying settings affects the trade-off between patient privacy and data utility

Abstract: Protecting healthcare data from inference attacks, where adversaries deduce sensitive information from de-identified data, is critical. This study examines the vulnerability of such datasets, focusing on Tennessee facilities serving predominantly African American populations, \textcolor{black}{while also incorporating analyses based on the MIMIC-III dataset representing Massachusetts}. We apply differential privacy with varying $\epsilon$ values to assess its impact on statistical integrity and predictive model accuracy. Results show a clear trade-off: lower $\epsilon$ enhances privacy but degrades performance, while higher $\epsilon$ preserves utility at the cost of increased leakage risk. These findings underscore the importance of carefully balancing privacy and utility when allocating the privacy budget in clinical prediction tasks.

Track: 2. Bioinformatics

Registration Id: KHNTWLH4HHT

Submission Number: 230