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

Ekaterina Shumitskaya, Anastasia Antsiferova, Dmitriy S. Vatolin
2/12/2026

No official code found. Best implementation: katiashh/ioi-attack (4 stars, last commit 2024-07-18).

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.

View on arXivView PDF

Code Implementations(1)

katiashh/ioi-attackCommunity100%

Official implementation of the paper "IOI: Invisible One-Iteration Adversarial Attack on No-Reference Image- and Video-Quality Metrics" (ICML 2024)

40Jupyter NotebookMay 24, 20242 years ago

Similar Papers

Cite this paper

@article{shumitskaya2026ioi,
  title  = {IOI: Invisible One-Iteration Adversarial Attack on No-Reference Image- and Video-Quality Metrics},
  author = {Ekaterina Shumitskaya and Anastasia Antsiferova and Dmitriy S. Vatolin},
  year   = {2026},
  eprint = {2403.05955},
  archivePrefix = {arXiv},
  url    = {https://arxiv.org/abs/2403.05955},
  journal = {ICML 2024 2024}
}

Add a badge to your README

Shows whether official code is linked for this paper.

Code of Paper badge
[![Code of Paper](https://codeofpaper.com/badge/2403.05955.svg)](https://codeofpaper.com/paper/2403.05955)

Discussion