Adversarial patches that work in the real world against video quality metrics and smart-camera systems.
Digital attacks assume full access to the input image, but real systems see the world through a camera. We proposed Ti-patch, a tiled physical adversarial patch against no-reference video quality metrics (Leonenkova et al., 2024), and demonstrated physical-digital patch attacks on real-world cameras at PerCom 2026.
References
2024
arXiv
Ti-patch: Tiled physical adversarial patch for no-reference video quality metrics
Victoria Leonenkova, Ekaterina Shumitskaya, Anastasia Antsiferova, and Dmitriy Vatolin
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 experiments both in pixel and physical space. We also performed experiments on the implementation of physical adversarial wallpaper. The proposed method can be used as additional quality metrics in vulnerability evaluation, complementing traditional subjective comparison and vulnerability tests in the pixel space. We made our code and adversarial videos available on GitHub: https://github.com/leonenkova/Ti-Patch.
@misc{vatolinTipatch2024,title={{Ti-patch: Tiled physical adversarial patch for no-reference video quality metrics}},author={Leonenkova, Victoria and Shumitskaya, Ekaterina and Antsiferova, Anastasia and Vatolin, Dmitriy},year={2024},journal={arXiv preprint arXiv:2404.09961},}