Adversarial Attacks on Medical Hyperspectral Imaging Exploiting Spectral-Spatial Dependencies and Multiscale Features

TL;DR

This paper introduces a structured adversarial attack framework tailored for medical hyperspectral imaging, exploiting spectral-spatial dependencies and multiscale features to reveal robustness weaknesses in current models.

Contribution

It proposes a novel attack method that models local spectral-spatial dependencies and hierarchical features to generate more effective adversarial examples for MHSI.

Findings

More effectively degrades lesion classification in tumor regions.

Reveals robustness weaknesses in current MHSI models.

Maintains low perturbation magnitude while attacking.

Abstract

Medical hyperspectral imaging (MHSI) has shown strong potential for disease diagnosis by capturing spectral-spatial information of tissues. While deep learning has substantially improved MHSI classification accuracy, its robustness remains limited due to the well-known trade-off between accuracy and robustness in Deep Neural Networks (DNNs). This issue is particularly critical in MHSI, where reliable prediction depends on local tissue relationships and multiscale spectral-spatial structures. A practical way to improve robustness is to identify the most unstable adversarial examples and incorporate them into adversarial training. However, existing attack methods do not sufficiently exploit these MHSI-specific properties, leading to suboptimal attack effectiveness and limited value for robustness enhancement. To address this gap, we propose a structured adversarial attack framework for MHSI that progressively models its local spectral-spatial dependencies and multiscale hierarchical representations. The proposed method generates anatomically consistent perturbations by modeling neighborhood dependencies and hierarchical spectral-spatial features. Experiments on the brain and choledoch datasets show that our method more effectively degrades lesion-related classification performance in critical tumor regions than existing baselines while maintaining low perturbation magnitude. These results reveal a clinically relevant robustness weakness in current MHSI models and provide stronger adversarial samples for developing targeted defense strategies.