Attention-guided single-voxel attacks for 3-dimensional neural networks: Experiments with post-mortem CT segmentation

Deep learning algorithms for detection and segmentation have been shown to be vulnerable to single-pixel attacks. These attacks can lead to catastrophic failure of the deep learning algorithm. In the case of biomedical imaging, this can result in significant damage to clinical outcomes. While single-pixel attacks have been studied within the field of digital pathology, they have yet to be studied within the realm of radiology, in particular with volumetric U-Net or V-Net architectures. In this work, we demonstrated that using gradcam++, we could identify vulnerable voxels for the single-voxel attacks that were slightly negative in value towards the boundary of kidney segmentations that lead to the significant distortion of the output kidney classification. Figure 1 demonstrates the graphical abstract for this work.