Attention-Guided Black-Box Adversarial Attacks with Large-Scale Multiobjective Evolutionary Optimization
Abstract
Recent black-box adversarial attacks may struggle to balance their attack ability and visual quality of the generated adversarial examples (AEs) in tackling high-resolution images. In this paper, We propose an attention-guided black-box adversarial attack based on the large-scale multiobjective evolutionary optimization, termed as LMOA. By considering the spatial semantic information of images, we firstly take advantage of the attention map to determine the perturbed pixels. Then, a large-scale multiobjective evolutionary algorithm is employed to traverse the reduced pixels in the salient region. Extensive experimental results have verified the effectiveness of the proposed LMOA on the ImageNet dataset.
Cite
Text
Wang et al. "Attention-Guided Black-Box Adversarial Attacks with Large-Scale Multiobjective Evolutionary Optimization." ICML 2021 Workshops: AML, 2021.Markdown
[Wang et al. "Attention-Guided Black-Box Adversarial Attacks with Large-Scale Multiobjective Evolutionary Optimization." ICML 2021 Workshops: AML, 2021.](https://mlanthology.org/icmlw/2021/wang2021icmlw-attentionguided/)BibTeX
@inproceedings{wang2021icmlw-attentionguided,
title = {{Attention-Guided Black-Box Adversarial Attacks with Large-Scale Multiobjective Evolutionary Optimization}},
author = {Wang, Jie and Yin, Zhaoxia and Jiang, Jing and Du, Yang},
booktitle = {ICML 2021 Workshops: AML},
year = {2021},
url = {https://mlanthology.org/icmlw/2021/wang2021icmlw-attentionguided/}
}