IOI: Invisible One-Iteration Adversarial Attack on No-Reference Image- and Video-Quality Metrics

TL;DR

This paper presents IOI, a fast and imperceptible adversarial attack targeting no-reference image and video quality metrics, demonstrating superior visual quality and effectiveness compared to prior methods.

Contribution

Introduces IOI, a novel one-iteration adversarial attack that is fast, imperceptible, and effective against no-reference image and video quality metrics.

Findings

IOI outperforms previous attacks in visual quality.

IOI maintains high attack success rate.

IOI operates with comparable speed to existing methods.

Abstract

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.