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

Medical hyperspectral imaging (HSI) enables accurate disease diagnosis by capturing rich spectral-spatial tissue information, but recent advances in deep learning have exposed its vulnerability to adversarial attacks. In this work, we identify two fundamental causes of this fragility: the reliance on local pixel dependencies for preserving tissue structure and the dependence on multiscale spectral-spatial representations for hierarchical feature encoding. Building on these insights, we propose a targeted adversarial attack framework for medical HSI, consisting of a Local Pixel Dependency Attack that exploits spatial correlations among neighboring pixels, and a Multiscale Information Attack that perturbs features across hierarchical spectral-spatial scales. Experiments on the Brain and MDC datasets demonstrate that our attacks significantly degrade classification performance, especially in tumor regions, while remaining visually imperceptible. Compared with existing methods, our approach reveals the unique vulnerabilities of medical HSI models and underscores the need for robust, structure-aware defenses in clinical applications.

Key Contributions

• Identification of two fundamental fragility causes in medical HSI models: reliance on local pixel spatial dependencies and multiscale spectral-spatial feature hierarchies
• Local Pixel Dependency Attack that crafts perturbations exploiting spatial correlations among neighboring pixels to disrupt tissue structure representations
• Multiscale Information Attack that perturbs hierarchical spectral-spatial features across multiple scales to degrade model classification

🛡️ Threat Analysis

Details

Similar Papers