Papers
Topics
Authors
Recent
Gemini 2.5 Flash
Gemini 2.5 Flash
119 tokens/sec
GPT-4o
56 tokens/sec
Gemini 2.5 Pro Pro
43 tokens/sec
o3 Pro
6 tokens/sec
GPT-4.1 Pro
47 tokens/sec
DeepSeek R1 via Azure Pro
28 tokens/sec
2000 character limit reached

Exploring Vulnerabilities of No-Reference Image Quality Assessment Models: A Query-Based Black-Box Method (2401.05217v3)

Published 10 Jan 2024 in cs.CV and eess.IV

Abstract: No-Reference Image Quality Assessment (NR-IQA) aims to predict image quality scores consistent with human perception without relying on pristine reference images, serving as a crucial component in various visual tasks. Ensuring the robustness of NR-IQA methods is vital for reliable comparisons of different image processing techniques and consistent user experiences in recommendations. The attack methods for NR-IQA provide a powerful instrument to test the robustness of NR-IQA. However, current attack methods of NR-IQA heavily rely on the gradient of the NR-IQA model, leading to limitations when the gradient information is unavailable. In this paper, we present a pioneering query-based black box attack against NR-IQA methods. We propose the concept of score boundary and leverage an adaptive iterative approach with multiple score boundaries. Meanwhile, the initial attack directions are also designed to leverage the characteristics of the Human Visual System (HVS). Experiments show our method outperforms all compared state-of-the-art attack methods and is far ahead of previous black-box methods. The effective NR-IQA model DBCNN suffers a Spearman's rank-order correlation coefficient (SROCC) decline of 0.6381 attacked by our method, revealing the vulnerability of NR-IQA models to black-box attacks. The proposed attack method also provides a potent tool for further exploration into NR-IQA robustness.

Definition Search Book Streamline Icon: https://streamlinehq.com
References (40)
  1. Learning to attack: Adversarial transformation networks. In AAAI Conference on Artificial Intelligence, volume 32, pages 2687–2695, 2018.
  2. John Canny. A computational approach to edge detection. IEEE Transactions on Pattern Analysis and Machine Intelligence, PAMI-8(6):679–698, 1986.
  3. ZOO: Zeroth order optimization based black-box attacks to deep neural networks without training substitute models. In ACM Workshop on Artificial Intelligence and Security, pages 15–26, 2017.
  4. Yu Deng and Ke Chen. Image quality analysis for searches, November 25 2014. US Patent 8,897,604.
  5. Image quality assessment: Unifying structure and texture similarity. IEEE Transactions on Pattern Analysis and Machine Intelligence, 44(5):2567–2581, 2022.
  6. Greedyfool: Distortion-aware sparse adversarial attack. Advances in Neural Information Processing Systems, 33:11226–11236, 2020.
  7. A no-reference objective image sharpness metric based on the notion of just noticeable blur (JNB). IEEE Transactions on Image Processing, 18(4):717–728, 2009.
  8. Massive online crowdsourced study of subjective and objective picture quality. IEEE Transactions on Image Processing, 25(1):372–387, 2016.
  9. Image quality assessment for perceptual image restoration: A new dataset, benchmark and metric. arXiv preprint arXiv:2011.15002, 2020.
  10. Simple black-box adversarial attacks. In International Conference on Machine Learning, pages 2484–2493, 2019.
  11. Adversarial attacks against blind image quality assessment models. In Proceedings of the 2nd Workshop on Quality of Experience in Visual Multimedia Applications, pages 3–11, 2022.
  12. Which has better visual quality: The clear blue sky or a blurry animal? IEEE Transactions on Multimedia, 21(5):1221–1234, 2019.
  13. Decision-based adversarial attack with frequency mixup. IEEE Transactions on Information Forensics and Security, 17:1038–1052, 2022.
  14. KADID-10k: A large-scale artificially distorted IQA database. In International Conference on Quality of Multimedia Experience, pages 1–3, 2019.
  15. Just noticeable difference for images with decomposition model for separating edge and textured regions. IEEE Transactions on Circuits and Systems for Video Technology, 20(11):1648–1652, 2010.
  16. Image quality assessment using contrastive learning. IEEE Transactions on Image Processing, 31:4149–4161, 2022.
  17. SurFree: A fast surrogate-free black-box attack. In IEEE/CVF Conference on Computer Vision and Pattern Recognition, pages 10430–10439, 2021.
  18. No-reference image quality assessment in the spatial domain. IEEE Transactions on Image Processing, 21(12):4695–4708, 2012.
  19. SparseFool: A few pixels make a big difference. In IEEE/CVF conference on computer vision and pattern recognition, pages 9087–9096, 2019.
  20. Blind image quality assessment: From natural scene statistics to perceptual quality. IEEE Transactions on Image Processing, 20(12):3350–3364, 2011.
  21. Transferability in machine learning: From phenomena to black-box attacks using adversarial samples. arXiv preprint arXiv:1605.07277, 2016.
  22. Practical black-box attacks against machine learning. In ACM on Asia Conference on Computer and Communications Security, pages 506–519, 2017.
  23. On the generation of adversarial examples for image quality assessment. The Visual Computer, pages 1–16, 2023.
  24. A novel just-noticeable-difference-based saliency-channel attention residual network for full-reference image quality predictions. IEEE Transactions on Circuits and Systems for Video Technology, 31(7):2602–2616, 2021.
  25. Image information and visual quality. IEEE Transactions on Image Processing, 15(2):430–444, 2006.
  26. A statistical evaluation of recent full reference image quality assessment algorithms. IEEE Transactions on Image Processing, 15(11):3440–3451, 2006.
  27. Universal perturbation attack on differentiable no-reference image- and video-quality metrics. In British Machine Vision Conference, pages 1–12, 2022.
  28. Blindly assess image quality in the wild guided by a self-adaptive hyper network. In IEEE/CVF Conference on Computer Vision and Pattern Recognition, pages 3667–3676, 2020.
  29. Intriguing properties of neural networks. In International Conference on Learning Representations, pages 1–10, 2014.
  30. Image quality assessment: From error visibility to structural similarity. IEEE Transactions on Image Processing, 13(4):600–612, 2004.
  31. Exploring CLIP for assessing the look and feel of images. In AAAI Conference on Artificial Intelligence, volume 37, pages 2555–2563, 2023.
  32. Improving transferability of adversarial examples with input diversity. In IEEE/CVF conference on computer vision and pattern recognition, pages 2730–2739, 2019.
  33. Unsupervised feature learning framework for no-reference image quality assessment. In IEEE conference on computer vision and pattern recognition, pages 1098–1105, 2012.
  34. From patches to pictures (PaQ-2-PiQ): Mapping the perceptual space of picture quality. In IEEE/CVF Conference on Computer Vision and Pattern Recognition, pages 3575–3585, 2020.
  35. FSIM: A feature similarity index for image quality assessment. IEEE Transactions on Image Processing, 20(8):2378–2386, 2011.
  36. Minimum barrier salient object detection at 80 FPS. In IEEE International Conference on Computer Vision, pages 1404–1412, 2015.
  37. The unreasonable effectiveness of deep features as a perceptual metric. In IEEE Conference on Computer Vision and Pattern Recognition, pages 586–595, 2018.
  38. Blind image quality assessment using a deep bilinear convolutional neural network. IEEE Transactions on Circuits and Systems for Video Technology, 30(1):36–47, 2020.
  39. Uncertainty-aware blind image quality assessment in the laboratory and wild. IEEE Transactions on Image Processing, 30:3474–3486, 2021.
  40. Perceptual attacks of no-reference image quality models with human-in-the-loop. Advances in Neural Information Processing Systems, 35:2916–2929, 2022.
User Edit Pencil Streamline Icon: https://streamlinehq.com
Authors (4)
  1. Chenxi Yang (14 papers)
  2. Yujia Liu (27 papers)
  3. Dingquan Li (18 papers)
  4. Tingting Jiang (27 papers)
Citations (5)
View on Semantic Scholar

Summary

We haven't generated a summary for this paper yet.

Ai Sparkles Streamline Icon: https://streamlinehq.com Summarize Now