DeepAI AI Chat
Log In Sign Up

Solving Inverse Problems With Deep Neural Networks – Robustness Included?

by   Martin Genzel, et al.

In the past five years, deep learning methods have become state-of-the-art in solving various inverse problems. Before such approaches can find application in safety-critical fields, a verification of their reliability appears mandatory. Recent works have pointed out instabilities of deep neural networks for several image reconstruction tasks. In analogy to adversarial attacks in classification, it was shown that slight distortions in the input domain may cause severe artifacts. The present article sheds new light on this concern, by conducting an extensive study of the robustness of deep-learning-based algorithms for solving underdetermined inverse problems. This covers compressed sensing with Gaussian measurements as well as image recovery from Fourier and Radon measurements, including a real-world scenario for magnetic resonance imaging (using the NYU-fastMRI dataset). Our main focus is on computing adversarial perturbations of the measurements that maximize the reconstruction error. A distinctive feature of our approach is the quantitative and qualitative comparison with total-variation minimization, which serves as a provably robust reference method. In contrast to previous findings, our results reveal that standard end-to-end network architectures are not only resilient against statistical noise, but also against adversarial perturbations. All considered networks are trained by common deep learning techniques, without sophisticated defense strategies.


page 8

page 17

page 19

page 20

page 21

page 22

page 24

page 25


Localized adversarial artifacts for compressed sensing MRI

As interest in deep neural networks (DNNs) for image reconstruction task...

Adversarial Robustness of MR Image Reconstruction under Realistic Perturbations

Deep Learning (DL) methods have shown promising results for solving ill-...

Regularizing linear inverse problems with convolutional neural networks

Deep convolutional neural networks trained on large datsets have emerged...

Deep Learning-Based Solvability of Underdetermined Inverse Problems in Medical Imaging

Recently, with the significant developments in deep learning techniques,...

Improving Robustness of Deep-Learning-Based Image Reconstruction

Deep-learning-based methods for different applications have been shown v...

Adversarial Attack on Deep Learning-Based Splice Localization

Regarding image forensics, researchers have proposed various approaches ...

One-dimensional Deep Image Prior for Time Series Inverse Problems

We extend the Deep Image Prior (DIP) framework to one-dimensional signal...

Code Repositories


Official implementation of the paper "Solving Inverse Problems With Deep Neural Networks - Robustness Included?" by M. Genzel, J. Macdonald, and M. März (2020).

view repo