mlsanityData to 7 Oct 2026

On Adversarial Robustness of Deep Image Deblurring

arXiv 2210.02502 ↗First posted 5 Oct 2022cs.CV eess.IVcited by 7

Not on the map. Why?

Abstract (arXiv)

Recent approaches employ deep learning-based solutions for the recovery of a sharp image from its blurry observation. This paper introduces adversarial attacks against deep learning-based image deblurring methods and evaluates the robustness of these neural networks to untargeted and targeted attacks. We demonstrate that imperceptible distortion can significantly degrade the performance of state-of-the-art deblurring networks, even producing drastically different content in the output, indicating the strong need to include adversarially robust training not only in classification but also for image recovery.

Key facts. Cited by 7 papers in the map (data through 7 Oct 2026). Builds on 18 of its 28 references that are in the map. First posted on arXiv 5 Oct 2022.

Builds on

18 of 28 references.

References · 18

  1. 2014Adam: A Method for Stochastic Optimizationcited by 36,960
  2. 2014Explaining and Harnessing Adversarial Examplescited by 7,287
  3. 2017Towards Deep Learning Models Resistant to Adversarial Attackscited by 6,326
  4. 2013Intriguing properties of neural networkscited by 5,114
  5. 2021Multi-Stage Progressive Image Restorationcited by 813
  6. 2019DeblurGAN-v2: Deblurring (Orders-of-Magnitude) Faster and Bettercited by 361
  7. 2017Learning Proximal Operators: Using Denoising Networks for Regularizing Inverse Imaging Problemscited by 107
  8. 2016A Neural Approach to Blind Motion Deblurringcited by 69
  9. 2014Learning to Deblurcited by 66
  10. 2020Solving Inverse Problems With Deep Neural Networks -- Robustness Included?cited by 58
  11. 2019Lipschitz Certificates for Layered Network Structures Driven by Averaged Activation Operatorscited by 54
  12. 2018Blind Image Deconvolution using Deep Generative Priorscited by 40
6 more
  1. 2019Evaluating Robustness of Deep Image Super-Resolution against Adversarial Attackscited by 37
  2. 2021DWDN: Deep Wiener Deconvolution Network for Non-Blind Image Deblurringcited by 36
  3. 2018Deep Unfolding of a Proximal Interior Point Method for Image Restorationcited by 23
  4. 2020Improving Robustness of Deep-Learning-Based Image Reconstructioncited by 23
  5. 2018Learning Deep Gradient Descent Optimization for Image Deconvolutioncited by 18
  6. 2020End-to-end Interpretable Learning of Non-blind Image Deblurringcited by 16

Built on by

Cited by year

Citing papers per year: 2022: 1; 2023: 3; 2024: 3.

7 papers.

  1. 2022Reasons for the Superiority of Stochastic Estimators over Deterministic Ones: Robustness, Consistency and Perceptual Qualitycited by 13
  2. 2023Conditional Generative Models are Provably Robust: Pointwise Guarantees for Bayesian Inverse Problemscited by 12
  3. 2023On the unreasonable vulnerability of transformers for image restoration -- and an easy fixcited by 11
  4. 2023Learning Provably Robust Estimators for Inverse Problems via Jitteringcited by 8
  5. 2024Evaluating Adversarial Robustness of Low dose CT Recoverycited by 1
  6. 2024Robustness and Exploration of Variational and Machine Learning Approaches to Inverse Problems: An Overviewcited by 1
  7. 2024Adversarial Purification and Fine-tuning for Robust UDC Image Restorationcited by 0