IOI: Invisible One-Iteration Adversarial Attack on No-Reference Image- and Video-Quality Metrics
This work addresses the robustness of learning-based quality metrics in video processing benchmarks, though it appears incremental as it builds on existing attack methods.
The paper tackled the problem of adversarial attacks on no-reference image- and video-quality metrics by introducing the Invisible One-Iteration (IOI) attack, which demonstrated superior visual quality compared to eight prior methods while maintaining similar attack success and speed.
No-reference image- and video-quality metrics are widely used in video processing benchmarks. The robustness of learning-based metrics under video attacks has not been widely studied. In addition to having success, attacks that can be employed in video processing benchmarks must be fast and imperceptible. This paper introduces an Invisible One-Iteration (IOI) adversarial attack on no reference image and video quality metrics. We compared our method alongside eight prior approaches using image and video datasets via objective and subjective tests. Our method exhibited superior visual quality across various attacked metric architectures while maintaining comparable attack success and speed. We made the code available on GitHub: https://github.com/katiashh/ioi-attack.