mlsanityData to 7 Oct 2026

Deep Image Destruction: Vulnerability of Deep Image-to-Image Models against Adversarial Attacks

arXiv 2104.15022 ↗First posted 30 Apr 2021cs.CV eess.IVcited by 8

Not on the map. Why?

Abstract (arXiv)

Recently, the vulnerability of deep image classification models to adversarial attacks has been investigated. However, such an issue has not been thoroughly studied for image-to-image tasks that take an input image and generate an output image (e.g., colorization, denoising, deblurring, etc.) This paper presents comprehensive investigations into the vulnerability of deep image-to-image models to adversarial attacks. For five popular image-to-image tasks, 16 deep models are analyzed from various standpoints such as output quality degradation due to attacks, transferability of adversarial examples across different tasks, and characteristics of perturbations. We show that unlike image classification tasks, the performance degradation on image-to-image tasks largely differs depending on various factors, e.g., attack methods and task objectives. In addition, we analyze the effectiveness of conventional defense methods used for classification models in improving the robustness of the image-to-image models.

Key facts. Cited by 8 papers in the map (data through 7 Oct 2026). Builds on 27 of its 36 references that are in the map. First posted on arXiv 30 Apr 2021.

Builds on

27 of 36 references.

References · 27

  1. 2015Deep Residual Learning for Image Recognitioncited by 51,809
  2. 2014Very Deep Convolutional Networks for Large-Scale Image Recognitioncited by 15,267
  3. 2014ImageNet Large Scale Visual Recognition Challengecited by 8,441
  4. 2014Explaining and Harnessing Adversarial Examplescited by 7,287
  5. 2013Intriguing properties of neural networkscited by 5,114
  6. 2018MobileNetV2: Inverted Residuals and Linear Bottleneckscited by 4,773
  7. 2016Photo-Realistic Single Image Super-Resolution Using a Generative Adversarial Networkcited by 1,898
  8. 2017Enhanced Deep Residual Networks for Single Image Super-Resolutioncited by 1,543
  9. 2016Beyond a Gaussian Denoiser: Residual Learning of Deep CNN for Image Denoisingcited by 1,352
  10. 2018Image Super-Resolution Using Very Deep Residual Channel Attention Networkscited by 1,256
  11. 2016Colorful Image Colorizationcited by 1,113
  12. 2016Adversarial Machine Learning at Scalecited by 934
15 more
  1. 2016Universal adversarial perturbationscited by 774
  2. 2016Deep Multi-scale Convolutional Neural Network for Dynamic Scene Deblurringcited by 722
  3. 2017The Perception-Distortion Tradeoffcited by 582
  4. 2016Delving into Transferable Adversarial Examples and Black-box Attackscited by 530
  5. 2017Mitigating Adversarial Effects Through Randomizationcited by 382
  6. 2018Fast, Accurate, and Lightweight Super-Resolution with Cascading Residual Networkcited by 263
  7. 2021Enhancing the Transferability of Adversarial Attacks through Variance Tuningcited by 242
  8. 2020Bag of Tricks for Adversarial Trainingcited by 199
  9. 2016A study of the effect of JPG compression on adversarial imagescited by 196
  10. 2018Is Robustness the Cost of Accuracy? -- A Comprehensive Study on the Robustness of 18 Deep Image Classification Modelscited by 135
  11. 2018Low Frequency Adversarial Perturbationcited by 80
  12. 2021A Survey On Universal Adversarial Attackcited by 59
  13. 2019On the Effectiveness of Low Frequency Perturbationscited by 56
  14. 2019FDA: Feature Disruptive Attackcited by 55
  15. 2019Evaluating Robustness of Deep Image Super-Resolution against Adversarial Attackscited by 37

Built on by

Cited by year

Citing papers per year: 2021: 1; 2022: 2; 2023: 4; 2024: 0; 2025: 1.

8 papers.

  1. 2022Imaging through the Atmosphere using Turbulence Mitigation Transformercited by 31
  2. 2021Towards Robust Neural Image Compression: Adversarial Attack and Model Finetuningcited by 24
  3. 2023Physics-Driven Turbulence Image Restoration with Stochastic Refinementcited by 24
  4. 2022Reasons for the Superiority of Stochastic Estimators over Deterministic Ones: Robustness, Consistency and Perceptual Qualitycited by 13
  5. 2023On the unreasonable vulnerability of transformers for image restoration -- and an easy fixcited by 11
  6. 2023Learning Provably Robust Estimators for Inverse Problems via Jitteringcited by 8
  7. 2023Fooling the Image Dehazing Models by First Order Gradientcited by 3
  8. 2025On Inverse Problems, Parameter Estimation, and Domain Generalizationcited by 0