Text-Guided Diffusion-Based Adversarial Attacks on Chest X-Ray Images

2026-08-29

AI Summary

本文提出了一种基于文本引导的扩散生成对抗框架，用于在胸部X光图像上产生对抗样本，以测试多疾病分类器的鲁棒性，并揭示了人类与机器解释之间的临床重要差异。

Abstract

As artificial intelligence is increasingly integrated into chest X-ray (CXR) interpretation, triage, and clinical decision support, understanding its vulnerability to adversarial manipulation is critical for safe deployment. Existing robustness evaluations, however, predominantly rely on pixel-space attacks that introduce numerically constrained perturbations but may not represent plausible radiographic variation. This limitation is particularly important in multi-disease CXR classification, where models simultaneously evaluate multiple overlapping pathologies and adversarial failures may alter several diagnostic predictions. We propose a text-guided diffusion-based adversarial framework that optimizes learnable text conditioning while keeping the diffusion generator and target classifier frozen, enabling adversarial generation through a learned image prior rather than direct pixel manipulation. We evaluate the framework across multiple classifier architectures in both binary atelectasis and multi-disease CXR classification and compare it with FGSM, PGD, and Carlini-Wagner attacks. Our approach consistently produced the greatest degradation in classifier performance, reducing AUROC to 0.3885-0.5646 in binary classification and 0.4441-0.4878 in the multi-disease setting, while achieving superior image fidelity (SSIM 0.9080, LPIPS 0.1670, FID 51.23). Importantly, clinician interpretation remained unchanged for 95.9% of binary and 73.8% of multi-disease adversarial images despite substantial changes in model predictions. These findings reveal a clinically important discrepancy between human and machine interpretation and demonstrate the need to extend medical AI robustness evaluation beyond conventional pixel-space attacks toward generative threat models that can expose failures under visually and clinically plausible image variations.

Problem

• adversarial attacks
• chest X-ray
• artificial intelligence
• robustness evaluation
• multi-disease classification

Innovation

• text-guided
• diffusion-based
• adversarial attacks
• chest X-ray images
• learnable text conditioning