Solving Inverse Problems With Deep Neural Networks -- Robustness Included?

Abstract

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.

References in corpus (6)

• Compressed Sensing using Generative Models
• Differentiable Convex Optimization Layers
• dAUTOMAP: decomposing AUTOMAP to achieve scalability and enhance performance
• $\Sigma$-net: Systematic Evaluation of Iterative Deep Neural Networks for Fast Parallel MR Image Reconstruction
• Improving Robustness of Deep-Learning-Based Image Reconstruction
• Total Deep Variation: A Stable Regularizer for Inverse Problems

Cited by in corpus (18)

• Can stable and accurate neural networks be computed? -- On the barriers of deep learning and Smale's 18th problem
• Measuring Robustness in Deep Learning Based Compressive Sensing
• An unsupervised deep learning algorithm for single-site reconstruction in quantum gas microscopes
• A Comparative Study of Deep Learning and Iterative Algorithms for Joint Channel Estimation and Signal Detection in OFDM Systems
• NESTANets: Stable, accurate and efficient neural networks for analysis-sparse inverse problems
• Representing Noisy Image Without Denoising
• On Instabilities of Conventional Multi-Coil MRI Reconstruction to Small Adverserial Perturbations
• MCMC-Net: Accelerating Markov Chain Monte Carlo with Neural Networks for Inverse Problems
• Inverting the Kohn-Sham equations with physics-informed machine learning
• Localized adversarial artifacts for compressed sensing MRI
• Evaluating Similitude and Robustness of Deep Image Denoising Models via Adversarial Attack
• Let's Enhance: A Deep Learning Approach to Extreme Deblurring of Text Images
• Gradient-Based Learning of Discrete Structured Measurement Operators for Signal Recovery
• Inversion of Integral Models: a Neural Network Approach
• Stabilizing Deep Tomographic Reconstruction
• Stability Bounds for the Unfolded Forward-Backward Algorithm
• On $L^{\infty }$ stability for wave propagation and for linear inverse problems
• AAPM DL-Sparse-View CT Challenge Submission Report: Designing an Iterative Network for Fanbeam-CT with Unknown Geometry