Adversarial Exposure Attack on Diabetic Retinopathy Imagery Grading

TL;DR

This paper introduces a novel adversarial exposure attack that manipulates retinal images to mislead deep neural networks in diabetic retinopathy grading, highlighting vulnerabilities and guiding future robustness improvements.

Contribution

It presents the first adversarial exposure attack method targeting DR grading DNNs, demonstrating high success in real-world scenarios and exposing security risks.

Findings

The attack achieves high transfer success rates across multiple DNN architectures.

Generated images maintain natural exposure appearance while fooling models.

The method exposes potential security threats in automated DR diagnosis systems.

Abstract

Diabetic Retinopathy (DR) is a leading cause of vision loss around the world. To help diagnose it, numerous cutting-edge works have built powerful deep neural networks (DNNs) to automatically grade DR via retinal fundus images (RFIs). However, RFIs are commonly affected by camera exposure issues that may lead to incorrect grades. The mis-graded results can potentially pose high risks to an aggravation of the condition. In this paper, we study this problem from the viewpoint of adversarial attacks. We identify and introduce a novel solution to an entirely new task, termed as adversarial exposure attack, which is able to produce natural exposure images and mislead the state-of-the-art DNNs. We validate our proposed method on a real-world public DR dataset with three DNNs, e.g., ResNet50, MobileNet, and EfficientNet, demonstrating that our method achieves high image quality and success rate in transferring the attacks. Our method reveals the potential threats to DNN-based automatic DR grading and would benefit the development of exposure-robust DR grading methods in the future.