paper-with-me

Papers

Fast Adversarial CNN-based Perturbation Attack of No-Reference Image Quality Metrics

2023-04-11 · ICLR: Tiny Papers 2023 4 · Ekaterina Shumitskaya, Anastasia Antsiferova, Dmitriy S. Vatolin

Modern neural-network-based no-reference image- and video-quality metrics exhibit performance as high as full-reference metrics. These metrics are widely used to improve visual quality in computer vision methods and compare video processing methods. However, these metrics are not stable to traditional adversarial attacks, which can cause incorrect results. Our goal is to investigate the boundaries of no-reference metrics applicability, and in this paper, we propose a fast adversarial perturbation attack of no-reference quality metrics. The proposed attack (FACPA) can be exploited as a preprocessing step in real-time video processing and compression algorithms. This research can yield insights to further aid in designing of stable neural-network-based no-reference quality metrics.

📄 PDF Abstract BibTeX

Code (1)

katiashh/FACPA pytorch

Tasks

Adversarial AttackNo-Reference Image Quality Assessment

Similar Papers 제목 키워드 기반

Fast Adversarial CNN-based Perturbation Attack on No-Reference Image- and Video-Quality Metrics

2023-05-24 · Ekaterina Shumitskaya, Anastasia Antsiferova, Dmitriy Vatolin

Modern neural-network-based no-reference image- and video-quality metrics exhibit performance as high as full-reference metrics. These metrics are widely used to improve visual quality in computer vision methods and comp…

Towards adversarial robustness verification of no-reference image-and video-quality metrics

2023-12-30 · Computer Vision and Image Understanding 2023 12 · Ekaterina Shumitskaya, Anastasia Antsiferova, Dmitriy Vatolin

In this paper, we propose a new method of analysing the stability of modern deep image- and video-quality metrics to different adversarial attacks. The stability analysis of quality metrics is becoming important because …

Adversarial AttackAdversarial RobustnessNo-Reference Image Quality Assessment

Attacking Perceptual Similarity Metrics

2023-05-15 · Abhijay Ghildyal, Feng Liu

Perceptual similarity metrics have progressively become more correlated with human judgments on perceptual similarity; however, despite recent advances, the addition of an imperceptible distortion can still compromise th…

Adversarial AttackExperimental Design

Aug-ILA: More Transferable Intermediate Level Attacks with Augmented References

2021-09-29 · Chiu Wai Yan, Dit-yan Yeung

An intriguing property of deep neural networks is that adversarial attacks can transfer across different models. Existing methods such as the Intermediate Level Attack (ILA) further improve black-box transferability by f…

Adversarial AttackImage Augmentation

Universal Perturbation Attack on Differentiable No-Reference Image- and Video-Quality Metrics

2022-11-01 · Ekaterina Shumitskaya, Anastasia Antsiferova, Dmitriy Vatolin

Universal adversarial perturbation attacks are widely used to analyze image classifiers that employ convolutional neural networks. Nowadays, some attacks can deceive image- and video-quality metrics. So sustainability an…

Adversarial AttackNo-Reference Image Quality Assessment