Enregistré dans:
Détails bibliographiques
Auteurs principaux: Gushchin, Aleksandr, Chistyakova, Anna, Minashkin, Vladislav, Antsiferova, Anastasia, Vatolin, Dmitriy
Format: Preprint
Publié: 2024
Sujets:
Accès en ligne:https://arxiv.org/abs/2404.06957
Tags: Ajouter un tag
Pas de tags, Soyez le premier à ajouter un tag!
_version_ 1866916199501135872
author Gushchin, Aleksandr
Chistyakova, Anna
Minashkin, Vladislav
Antsiferova, Anastasia
Vatolin, Dmitriy
author_facet Gushchin, Aleksandr
Chistyakova, Anna
Minashkin, Vladislav
Antsiferova, Anastasia
Vatolin, Dmitriy
contents Recently, the area of adversarial attacks on image quality metrics has begun to be explored, whereas the area of defences remains under-researched. In this study, we aim to cover that case and check the transferability of adversarial purification defences from image classifiers to IQA methods. In this paper, we apply several widespread attacks on IQA models and examine the success of the defences against them. The purification methodologies covered different preprocessing techniques, including geometrical transformations, compression, denoising, and modern neural network-based methods. Also, we address the challenge of assessing the efficacy of a defensive methodology by proposing ways to estimate output visual quality and the success of neutralizing attacks. Defences were tested against attack on three IQA metrics -- Linearity, MetaIQA and SPAQ. The code for attacks and defences is available at: (link is hidden for a blind review).
format Preprint
id arxiv_https___arxiv_org_abs_2404_06957
institution arXiv
publishDate 2024
record_format arxiv
spellingShingle Adversarial purification for no-reference image-quality metrics: applicability study and new methods
Gushchin, Aleksandr
Chistyakova, Anna
Minashkin, Vladislav
Antsiferova, Anastasia
Vatolin, Dmitriy
Computer Vision and Pattern Recognition
Artificial Intelligence
Recently, the area of adversarial attacks on image quality metrics has begun to be explored, whereas the area of defences remains under-researched. In this study, we aim to cover that case and check the transferability of adversarial purification defences from image classifiers to IQA methods. In this paper, we apply several widespread attacks on IQA models and examine the success of the defences against them. The purification methodologies covered different preprocessing techniques, including geometrical transformations, compression, denoising, and modern neural network-based methods. Also, we address the challenge of assessing the efficacy of a defensive methodology by proposing ways to estimate output visual quality and the success of neutralizing attacks. Defences were tested against attack on three IQA metrics -- Linearity, MetaIQA and SPAQ. The code for attacks and defences is available at: (link is hidden for a blind review).
title Adversarial purification for no-reference image-quality metrics: applicability study and new methods
topic Computer Vision and Pattern Recognition
Artificial Intelligence
url https://arxiv.org/abs/2404.06957