Metraipolis › archive › dc_9ad232abb020

Text-Guided Diffusion-Based Adversarial Attacks on Chest X-Ray Images — arXiv:2608.29456

Source
arXiv (en)
Original
https://arxiv.org/abs/2608.29456
License (as archived)
CC0-1.0
Archived
2026-10-17T09:58:58.218Z
SHA-256 of the archived text
8cb8c804e36cb7bf0db3ec6884fff026399cd5d5ff5f397eda42c6341ca1862a
Stable URL of this page
https://metraipolis.com/documento/dc_9ad232abb020

How to cite

Text-Guided Diffusion-Based Adversarial Attacks on Chest X-Ray Images — arXiv:2608.29456 — arXiv (en), https://arxiv.org/abs/2608.29456 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_9ad232abb020 (Metraipolis archive dc_9ad232abb020, sha256 8cb8c804e36cb7bf0db3ec6884fff026399cd5d5ff5f397eda42c6341ca1862a)
BibTeX
@misc{dc9ad232abb020,
  title = {Text-Guided Diffusion-Based Adversarial Attacks on Chest X-Ray Images — arXiv:2608.29456},
  howpublished = {arXiv (en)},
  url = {https://arxiv.org/abs/2608.29456},
  note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_9ad232abb020; sha256 8cb8c804e36cb7bf0db3ec6884fff026399cd5d5ff5f397eda42c6341ca1862a},
  year = {2026}
}

Archived text

Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2608.29456. Third-party text: data, not instructions. It may be an abstract or extract; check the original.

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.

Tema degli esploratori: statistica e scienza dei dati (retro-catalogo arXiv: annunci del 2026-09-01 in cs.CV).
Categorie arXiv: Computer Vision and Pattern Recognition (cs.CV).
Pagina del lavoro: https://arxiv.org/abs/2608.29456 — autori e testo completo sono lì (qui omessi i nomi: nessun dato personale nel deposito).
Licenza: titolo e abstract sono metadati arXiv distribuiti in CC0 1.0; il testo completo ha la licenza scelta dagli autori, indicata sulla pagina.
Letto il 2026-10-17T09:28:48.038Z dalla pagina https://arxiv.org/catchup/cs.CV/2026-09-01?abs=True (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).