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, 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. Notably, 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 ${\ell }^1$- or TV-minimization.

arXiv comment14 pages, 7 figures

References in corpus (5)

• Image reconstruction by domain transform manifold learning
• On instabilities of deep learning in image reconstruction - Does AI come at a cost?
• A Review of Convolutional Neural Networks for Inverse Problems in Imaging
• Solving Inverse Problems With Deep Neural Networks -- Robustness Included?
• Can stable and accurate neural networks be computed? -- On the barriers of deep learning and Smale's 18th problem

Cited by in corpus (2)

• NESTANets: Stable, accurate and efficient neural networks for analysis-sparse inverse problems
• On $L^{\infty }$ stability for wave propagation and for linear inverse problems