Ti-Patch: Tiled Physical Adversarial Patch for no-reference video quality metrics
Victoria Leonenkova, Ekaterina Shumitskaya, Anastasia Antsiferova,, Dmitriy Vatolin

TL;DR
This paper introduces Ti-Patch, a novel tiled physical adversarial patch that tests the vulnerability of no-reference video quality metrics in physical space, revealing their susceptibility beyond pixel-level attacks.
Contribution
The paper presents the first method for testing quality metrics' vulnerability to physical adversarial patches, expanding analysis from pixel to physical space.
Findings
Physical adversarial patches can deceive quality metrics in real-world settings.
Physical space attacks reveal vulnerabilities not detectable in pixel-based tests.
The method enhances the evaluation of metric robustness in practical scenarios.
Abstract
Objective no-reference image- and video-quality metrics are crucial in many computer vision tasks. However, state-of-the-art no-reference metrics have become learning-based and are vulnerable to adversarial attacks. The vulnerability of quality metrics imposes restrictions on using such metrics in quality control systems and comparing objective algorithms. Also, using vulnerable metrics as a loss for deep learning model training can mislead training to worsen visual quality. Because of that, quality metrics testing for vulnerability is a task of current interest. This paper proposes a new method for testing quality metrics vulnerability in the physical space. To our knowledge, quality metrics were not previously tested for vulnerability to this attack; they were only tested in the pixel space. We applied a physical adversarial Ti-Patch (Tiled Patch) attack to quality metrics and did…
Peer Reviews
No public reviews on file for this paper yet. If you reviewed it on a platform where reviews are public (OpenReview, ICLR, NeurIPS, ICML), you can paste yours below so the community can read it here.
Code & Models
Videos
No videos yet. Explain this paper in a talk, walkthrough, or lecture? Add one.
Taxonomy
TopicsAdversarial Robustness in Machine Learning
