mlsanityData to 14 Oct 2026

Adversarial purification for no-reference image-quality metrics: applicability study and new methods

arXiv 2404.06957 ↗First posted 10 Apr 2024cs.CV cs.AIcited by 5

Not on the map. Why?

Abstract (arXiv)

Recently, the area of adversarial attacks on image quality metrics has begun to be explored, whereas the area of defences remains under-researched. In this study, we aim to cover that case and check the transferability of adversarial purification defences from image classifiers to IQA methods. In this paper, we apply several widespread attacks on IQA models and examine the success of the defences against them. The purification methodologies covered different preprocessing techniques, including geometrical transformations, compression, denoising, and modern neural network-based methods. Also, we address the challenge of assessing the efficacy of a defensive methodology by proposing ways to estimate output visual quality and the success of neutralizing attacks. Defences were tested against attack on three IQA metrics -- Linearity, MetaIQA and SPAQ. The code for attacks and defences is available at: (link is hidden for a blind review).

Key facts. Cited by 5 papers in the map (data through 14 Oct 2026). Builds on 27 of its 42 references that are in the map. First posted on arXiv 10 Apr 2024.

Builds on

27 of 42 references.

References · 27

  1. 2018The Unreasonable Effectiveness of Deep Features as a Perceptual Metriccited by 11,177
  2. 2014Explaining and Harnessing Adversarial Examplescited by 7,364
  3. 2017Towards Deep Learning Models Resistant to Adversarial Attackscited by 6,415
  4. 2013Intriguing properties of neural networkscited by 5,155
  5. 2016Towards Evaluating the Robustness of Neural Networkscited by 2,998
  6. 2016Adversarial examples in the physical worldcited by 1,769
  7. 2021Real-ESRGAN: Training Real-World Blind Super-Resolution with Pure Synthetic Datacited by 970
  8. 2021Multi-Stage Progressive Image Restorationcited by 816
  9. 2020Image Quality Assessment: Unifying Structure and Texture Similaritycited by 811
  10. 2017Countering Adversarial Images using Input Transformationscited by 520
  11. 2017Feature Squeezing: Detecting Adversarial Examples in Deep Neural Networkscited by 486
  12. 2018Defense-GAN: Protecting Classifiers Against Adversarial Attacks Using Generative Modelscited by 362
15 more
  1. 2017MagNet: a Two-Pronged Defense against Adversarial Examplescited by 269
  2. 2016A study of the effect of JPG compression on adversarial imagescited by 197
  3. 2020MetaIQA: Deep Meta-learning for No-Reference Image Quality Assessmentcited by 144
  4. 2017Keeping the Bad Guys Out: Protecting and Vaccinating Deep Learning with JPEG Compressioncited by 87
  5. 2022Frequency-driven Imperceptible Adversarial Attack on Semantic Similaritycited by 77
  6. 2020Norm-in-Norm Loss with Faster Convergence and Better Performance for Image Quality Assessmentcited by 54
  7. 2019E-LPIPS: Robust Perceptual Image Similarity via Random Transformation Ensemblescited by 45
  8. 2022Perceptual Attacks of No-Reference Image Quality Models with Human-in-the-Loopcited by 30
  9. 2023R-LPIPS: An Adversarially Robust Perceptual Similarity Metriccited by 28
  10. 2022Video compression dataset and benchmark of learning-based video-quality metricscited by 27
  11. 2021Quantifying Visual Image Quality: A Bayesian Viewcited by 20
  12. 2022Universal Perturbation Attack on Differentiable No-Reference Image- and Video-Quality Metricscited by 17
  13. 2023Comparing the Robustness of Modern No-Reference Image- and Video-Quality Metrics to Adversarial Attackscited by 14
  14. 2016Assessing Threat of Adversarial Examples on Deep Neural Networkscited by 9
  15. 2019Hacking VMAF with Video Color and Contrast Distortioncited by 8

Built on by

Cited by year

Citing papers per year: 2024: 3; 2025: 2.

5 papers.

  1. 2024Guardians of Image Quality: Benchmarking Defenses Against Adversarial Attacks on Image Quality Metricscited by 5
  2. 2024Secure Video Quality Assessment Resisting Adversarial Attackscited by 1
  3. 2025SEGA: A Transferable Signed Ensemble Gaussian Black-Box Attack against No-Reference Image Quality Assessment Modelscited by 1
  4. 2024Stochastic BIQA: Median Randomized Smoothing for Certified Blind Image Quality Assessmentcited by 0
  5. 2025Robustness as Architecture: Designing IQA Models to Withstand Adversarial Perturbationscited by 0