English

Defending Medical Image Diagnostics against Privacy Attacks using Generative Methods

Cryptography and Security 2021-08-23 v2 Computer Vision and Pattern Recognition Computers and Society Machine Learning Image and Video Processing

Abstract

Machine learning (ML) models used in medical imaging diagnostics can be vulnerable to a variety of privacy attacks, including membership inference attacks, that lead to violations of regulations governing the use of medical data and threaten to compromise their effective deployment in the clinic. In contrast to most recent work in privacy-aware ML that has been focused on model alteration and post-processing steps, we propose here a novel and complementary scheme that enhances the security of medical data by controlling the data sharing process. We develop and evaluate a privacy defense protocol based on using a generative adversarial network (GAN) that allows a medical data sourcer (e.g. a hospital) to provide an external agent (a modeler) a proxy dataset synthesized from the original images, so that the resulting diagnostic systems made available to model consumers is rendered resilient to privacy attackers. We validate the proposed method on retinal diagnostics AI used for diabetic retinopathy that bears the risk of possibly leaking private information. To incorporate concerns of both privacy advocates and modelers, we introduce a metric to evaluate privacy and utility performance in combination, and demonstrate, using these novel and classical metrics, that our approach, by itself or in conjunction with other defenses, provides state of the art (SOTA) performance for defending against privacy attacks.

Keywords

Cite

@article{arxiv.2103.03078,
  title  = {Defending Medical Image Diagnostics against Privacy Attacks using Generative Methods},
  author = {William Paul and Yinzhi Cao and Miaomiao Zhang and Phil Burlina},
  journal= {arXiv preprint arXiv:2103.03078},
  year   = {2021}
}

Comments

Accepted for oral presentation at MICCAI PPML 2021

R2 v1 2026-06-23T23:45:20.261Z