GreedyPixel: Fine-Grained Black-Box Adversarial Attack Via Greedy Algorithm

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Wang, Hanrui, Chang, Ching-Chun, Lu, Chun-Shien, Leckie, Christopher, Echizen, Isao
Format: Preprint
Published: 2025
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866914255773630464
author Wang, Hanrui
Chang, Ching-Chun
Lu, Chun-Shien
Leckie, Christopher
Echizen, Isao
author_facet Wang, Hanrui
Chang, Ching-Chun
Lu, Chun-Shien
Leckie, Christopher
Echizen, Isao
contents Deep neural networks are highly vulnerable to adversarial examples, which are inputs with small, carefully crafted perturbations that cause misclassification -- making adversarial attacks a critical tool for evaluating robustness. Existing black-box methods typically entail a trade-off between precision and flexibility: pixel-sparse attacks (e.g., single- or few-pixel attacks) provide fine-grained control but lack adaptability, whereas patch- or frequency-based attacks improve efficiency or transferability, but at the cost of producing larger and less precise perturbations. We present GreedyPixel, a fine-grained black-box attack method that performs brute-force-style, per-pixel greedy optimization guided by a surrogate-derived priority map and refined by means of query feedback. It evaluates each coordinate directly without any gradient information, guaranteeing monotonic loss reduction and convergence to a coordinate-wise optimum, while also yielding near white-box-level precision and pixel-wise sparsity and perceptual quality. On the CIFAR-10 and ImageNet datasets, spanning convolutional neural networks (CNNs) and Transformer models, GreedyPixel achieved state-of-the-art success rates with visually imperceptible perturbations, effectively bridging the gap between black-box practicality and white-box performance. The implementation is available at https://github.com/azrealwang/greedypixel.
format Preprint
id arxiv_https___arxiv_org_abs_2501_14230
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle GreedyPixel: Fine-Grained Black-Box Adversarial Attack Via Greedy Algorithm
Wang, Hanrui
Chang, Ching-Chun
Lu, Chun-Shien
Leckie, Christopher
Echizen, Isao
Computer Vision and Pattern Recognition
Cryptography and Security
Machine Learning
Deep neural networks are highly vulnerable to adversarial examples, which are inputs with small, carefully crafted perturbations that cause misclassification -- making adversarial attacks a critical tool for evaluating robustness. Existing black-box methods typically entail a trade-off between precision and flexibility: pixel-sparse attacks (e.g., single- or few-pixel attacks) provide fine-grained control but lack adaptability, whereas patch- or frequency-based attacks improve efficiency or transferability, but at the cost of producing larger and less precise perturbations. We present GreedyPixel, a fine-grained black-box attack method that performs brute-force-style, per-pixel greedy optimization guided by a surrogate-derived priority map and refined by means of query feedback. It evaluates each coordinate directly without any gradient information, guaranteeing monotonic loss reduction and convergence to a coordinate-wise optimum, while also yielding near white-box-level precision and pixel-wise sparsity and perceptual quality. On the CIFAR-10 and ImageNet datasets, spanning convolutional neural networks (CNNs) and Transformer models, GreedyPixel achieved state-of-the-art success rates with visually imperceptible perturbations, effectively bridging the gap between black-box practicality and white-box performance. The implementation is available at https://github.com/azrealwang/greedypixel.
title GreedyPixel: Fine-Grained Black-Box Adversarial Attack Via Greedy Algorithm
topic Computer Vision and Pattern Recognition
Cryptography and Security
Machine Learning
url https://arxiv.org/abs/2501.14230