Salvato in:
Dettagli Bibliografici
Autori principali: Reza, Md Farhamdur, Jin, Richeng, Wu, Tianfu, Dai, Huaiyu
Natura: Preprint
Pubblicazione: 2025
Soggetti:
Accesso online:https://arxiv.org/abs/2503.12827
Tags: Aggiungi Tag
Nessun Tag, puoi essere il primo ad aggiungerne!!
_version_ 1866908387565895680
author Reza, Md Farhamdur
Jin, Richeng
Wu, Tianfu
Dai, Huaiyu
author_facet Reza, Md Farhamdur
Jin, Richeng
Wu, Tianfu
Dai, Huaiyu
contents Existing score-based adversarial attacks mainly focus on crafting $top$-1 adversarial examples against classifiers with single-label classification. Their attack success rate and query efficiency are often less than satisfactory, particularly under small perturbation requirements; moreover, the vulnerability of classifiers with multi-label learning is yet to be studied. In this paper, we propose a comprehensive surrogate free score-based attack, named \b geometric \b score-based \b black-box \b attack (GSBA$^K$), to craft adversarial examples in an aggressive $top$-$K$ setting for both untargeted and targeted attacks, where the goal is to change the $top$-$K$ predictions of the target classifier. We introduce novel gradient-based methods to find a good initial boundary point to attack. Our iterative method employs novel gradient estimation techniques, particularly effective in $top$-$K$ setting, on the decision boundary to effectively exploit the geometry of the decision boundary. Additionally, GSBA$^K$ can be used to attack against classifiers with $top$-$K$ multi-label learning. Extensive experimental results on ImageNet and PASCAL VOC datasets validate the effectiveness of GSBA$^K$ in crafting $top$-$K$ adversarial examples.
format Preprint
id arxiv_https___arxiv_org_abs_2503_12827
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle GSBA$^K$: $top$-$K$ Geometric Score-based Black-box Attack
Reza, Md Farhamdur
Jin, Richeng
Wu, Tianfu
Dai, Huaiyu
Computer Vision and Pattern Recognition
Existing score-based adversarial attacks mainly focus on crafting $top$-1 adversarial examples against classifiers with single-label classification. Their attack success rate and query efficiency are often less than satisfactory, particularly under small perturbation requirements; moreover, the vulnerability of classifiers with multi-label learning is yet to be studied. In this paper, we propose a comprehensive surrogate free score-based attack, named \b geometric \b score-based \b black-box \b attack (GSBA$^K$), to craft adversarial examples in an aggressive $top$-$K$ setting for both untargeted and targeted attacks, where the goal is to change the $top$-$K$ predictions of the target classifier. We introduce novel gradient-based methods to find a good initial boundary point to attack. Our iterative method employs novel gradient estimation techniques, particularly effective in $top$-$K$ setting, on the decision boundary to effectively exploit the geometry of the decision boundary. Additionally, GSBA$^K$ can be used to attack against classifiers with $top$-$K$ multi-label learning. Extensive experimental results on ImageNet and PASCAL VOC datasets validate the effectiveness of GSBA$^K$ in crafting $top$-$K$ adversarial examples.
title GSBA$^K$: $top$-$K$ Geometric Score-based Black-box Attack
topic Computer Vision and Pattern Recognition
url https://arxiv.org/abs/2503.12827