mlsanityData to 7 Oct 2026

Guardians of Image Quality: Benchmarking Defenses Against Adversarial Attacks on Image Quality Metrics

arXiv 2408.01541 ↗First posted 2 Aug 2024cs.CV eess.IVcited by 5

Not on the map. Why?

Abstract (arXiv)

In the field of Image Quality Assessment (IQA), the adversarial robustness of the metrics poses a critical concern. This paper presents a comprehensive benchmarking study of various defense mechanisms in response to the rise in adversarial attacks on IQA. We systematically evaluate 25 defense strategies, including adversarial purification, adversarial training, and certified robustness methods. We applied 14 adversarial attack algorithms of various types in both non-adaptive and adaptive settings and tested these defenses against them. We analyze the differences between defenses and their applicability to IQA tasks, considering that they should preserve IQA scores and image quality. The proposed benchmark aims to guide future developments and accepts submissions of new methods, with the latest results available online: https://videoprocessing.ai/benchmarks/iqa-defenses.html.

Key facts. Cited by 5 papers in the map (data through 7 Oct 2026). Builds on 47 of its 75 references that are in the map. First posted on arXiv 2 Aug 2024.

Builds on

47 of 75 references.

References · 47

  1. 2013Intriguing properties of neural networkscited by 5,114
  2. 2016Adversarial examples in the physical worldcited by 1,762
  3. 2023VBench: Comprehensive Benchmark Suite for Video Generative Modelscited by 1,755
  4. 2020Reliable evaluation of adversarial robustness with an ensemble of diverse parameter-free attackscited by 1,442
  5. 2019Certified Adversarial Robustness via Randomized Smoothingcited by 1,324
  6. 2022Exploring CLIP for Assessing the Look and Feel of Imagescited by 974
  7. 2021Real-ESRGAN: Training Real-World Blind Super-Resolution with Pure Synthetic Datacited by 961
  8. 2021Multi-Stage Progressive Image Restorationcited by 813
  9. 2020Fast is better than free: Revisiting adversarial trainingcited by 723
  10. 2019Square Attack: a query-efficient black-box adversarial attack via random searchcited by 682
  11. 2020RobustBench: a standardized adversarial robustness benchmarkcited by 659
  12. 2017One pixel attack for fooling deep neural networkscited by 579
35 more
  1. 2017Countering Adversarial Images using Input Transformationscited by 517
  2. 2022MANIQA: Multi-dimension Attention Network for No-Reference Image Quality Assessmentcited by 514
  3. 2018Black-box Adversarial Attacks with Limited Queries and Informationcited by 499
  4. 2017Feature Squeezing: Detecting Adversarial Examples in Deep Neural Networkscited by 484
  5. 2019KonIQ-10k: An ecologically valid database for deep learning of blind image quality assessmentcited by 351
  6. 2017Adversarial Attacks on Neural Network Policiescited by 314
  7. 2023SeeSR: Towards Semantics-Aware Real-World Image Super-Resolutioncited by 311
  8. 2019From Patches to Pictures (PaQ-2-PiQ): Mapping the Perceptual Space of Picture Qualitycited by 221
  9. 2023TOPIQ: A Top-down Approach from Semantics to Distortions for Image Quality Assessmentcited by 220
  10. 2020MetaIQA: Deep Meta-learning for No-Reference Image Quality Assessmentcited by 144
  11. 2023AGIQA-3K: An Open Database for AI-Generated Image Quality Assessmentcited by 142
  12. 2022(Certified!!) Adversarial Robustness for Free!cited by 130
  13. 2019Unrestricted Adversarial Examples via Semantic Manipulationcited by 84
  14. 2023Revisiting Adversarial Training for ImageNet: Architectures, Training and Generalization across Threat Modelscited by 79
  15. 2022Frequency-driven Imperceptible Adversarial Attack on Semantic Similaritycited by 76
  16. 2020Sparse-RS: a versatile framework for query-efficient sparse black-box adversarial attackscited by 65
  17. 2020Norm-in-Norm Loss with Faster Convergence and Better Performance for Image Quality Assessmentcited by 54
  18. 2019Parsimonious Black-Box Adversarial Attacks via Efficient Combinatorial Optimizationcited by 49
  19. 2020Detection as Regression: Certified Object Detection by Median Smoothingcited by 47
  20. 2022DensePure: Understanding Diffusion Models towards Adversarial Robustnesscited by 33
  21. 2022DISCO: Adversarial Defense with Local Implicit Functionscited by 33
  22. 2022Perceptual Attacks of No-Reference Image Quality Models with Human-in-the-Loopcited by 30
  23. 2022Video compression dataset and benchmark of learning-based video-quality metricscited by 27
  24. 2021No-Reference Image Quality Assessment by Hallucinating Pristine Featurescited by 16
  25. 2023Comparing the Robustness of Modern No-Reference Image- and Video-Quality Metrics to Adversarial Attackscited by 14
  26. 2023Differentiable JPEG: The Devil is in the Detailscited by 13
  27. 2023Vulnerabilities in Video Quality Assessment Models: The Challenge of Adversarial Attackscited by 12
  28. 2024Exploring Vulnerabilities of No-Reference Image Quality Assessment Models: A Query-Based Black-Box Methodcited by 10
  29. 2023Attacking Perceptual Similarity Metricscited by 8
  30. 2024Black-box Adversarial Attacks Against Image Quality Assessment Modelscited by 8
  31. 2022Reducing Certified Regression to Certified Classification for General Poisoning Attackscited by 7
  32. 2023Fast Adversarial CNN-based Perturbation Attack on No-Reference Image- and Video-Quality Metricscited by 7
  33. 2024Defense Against Adversarial Attacks on No-Reference Image Quality Models with Gradient Norm Regularizationcited by 7
  34. 2024Adversarial purification for no-reference image-quality metrics: applicability study and new methodscited by 5
  35. 2024Can No-Reference Quality-Assessment Methods Serve as Perceptual Losses for Super-Resolution?cited by 4

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2024: 2; 2025: 2; 2026: 1.

5 papers.

  1. 2025Augmenting Perceptual Super-Resolution via Image Quality Predictorscited by 7
  2. 2024Quality Prediction of AI Generated Images and Videos: Emerging Trends and Opportunitiescited by 3
  3. 2026BiRQA: Bidirectional Robust Quality Assessment for Imagescited 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