Localized adversarial artifacts for compressed sensing MRI

Understand

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, when appropriately regularized, DNNs show similar robustness to adversarial noise in terms of $\ell^2$-reconstruction error (Genzel et al., 2022).
• We consider a different notion of robustness, using the $\ell^\infty$-norm, and argue that localized reconstruction artifacts are a more relevant defect than the $\ell^2$-error.
• We create adversarial perturbations to undersampled magnetic resonance imaging measurements (in the frequency domain) which induce severe localized artifacts in the TV-regularized reconstruction.