CVMMIVMay 24, 2023

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

arXiv:2305.15544v112 citations
Originality Incremental advance
AI Analysis

This work addresses the stability of quality metrics for computer vision applications, but it is incremental as it builds on existing adversarial attack methods.

The authors tackled the vulnerability of neural-network-based no-reference image and video quality metrics to adversarial attacks by proposing a fast adversarial perturbation attack (FACPA), which can be used as a preprocessing step in real-time video processing and compression algorithms.

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 on 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.

Code Implementations1 repo
Foundations

The foundational work for this paper's niche, ranked by how specifically the neighbourhood builds on it — not by global fame.

Your Notes