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

ArXi:2601.07056v2 Announce Type: replace-cross 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.