Adversarial attacks on medical hyperspectral imaging exploiting spectral-spatial dependencies and multiscale features

Abstract

Abstract Medical hyperspectral imaging (MHSI) has demonstrated considerable promise in 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 hyperspectral human brain image (the Brain) dataset and the multidimensional choledoch (MDC) dataset show that our method degrades lesion-related classification performance in critical tumor regions more effectively 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.