Localized adversarial artifacts for compressed sensing MRI

Abstract

As interest in deep neural networks (DNNs) for image reconstruction tasks grows, their reliability has been called into question (Antun et al., 2020; Gottschling et al., 2020). However, recent work has shown that compared to total variation (TV) minimization, they show similar robustness to adversarial noise in terms of ℓ2-reconstruction error (Genzel et al., 2022). We consider a different notion of robustness, using the ℓ∞-norm, and argue that localized reconstruction artifacts are a more relevant defect than the ℓ2-error. We create adversarial perturbations to undersampled MRI measurements which induce severe localized artifacts in the TV-regularized reconstruction. The same attack method is not as effective against DNN based reconstruction. Finally, we show that this phenomenon is inherent to reconstruction methods for which exact recovery can be guaranteed, as with compressed sensing reconstructions with ℓ1- or TV-minimization.