English
Related papers

Related papers: Rethinking the Backward Propagation for Adversaria…

200 papers

We consider adversarial attacks to a black-box model when no queries are allowed. In this setting, many methods directly attack surrogate models and transfer the obtained adversarial examples to fool the target model. Plenty of previous…

Machine Learning · Computer Science 2021-09-08 Yunxiao Qin , Yuanhao Xiong , Jinfeng Yi , Cho-Jui Hsieh

Adversarial examples generated by a surrogate model typically exhibit limited transferability to unknown target systems. To address this problem, many transferability enhancement approaches (e.g., input transformation and model…

Computer Vision and Pattern Recognition · Computer Science 2024-02-07 Qinliang Lin , Cheng Luo , Zenghao Niu , Xilin He , Weicheng Xie , Yuanbo Hou , Linlin Shen , Siyang Song

Adversarial examples, which are slightly perturbed inputs generated with the aim of fooling a neural network, are known to transfer between models; adversaries which are effective on one model will often fool another. This concept of…

Machine Learning · Computer Science 2020-05-13 George Adam , Romain Speciel

Strong adversarial examples are crucial for evaluating and enhancing the robustness of deep neural networks. However, the performance of popular attacks is usually sensitive, for instance, to minor image transformations, stemming from…

Machine Learning · Computer Science 2024-04-01 Zhengwei Fang , Rui Wang , Tao Huang , Liping Jing

The transferability of adversarial examples across deep neural network (DNN) models is the crux of a spectrum of black-box attacks. In this paper, we propose a novel method to enhance the black-box transferability of baseline adversarial…

Computer Vision and Pattern Recognition · Computer Science 2020-08-21 Qizhang Li , Yiwen Guo , Hao Chen

The transferability of adversarial perturbations between image models has been extensively studied. In this case, an attack is generated from a known surrogate \eg, the ImageNet trained model, and transferred to change the decision of an…

Computer Vision and Pattern Recognition · Computer Science 2023-04-06 Muzammal Naseer , Ahmad Mahmood , Salman Khan , Fahad Khan

Transfer-based adversarial example is one of the most important classes of black-box attacks. However, there is a trade-off between transferability and imperceptibility of the adversarial perturbation. Prior work in this direction often…

Computer Vision and Pattern Recognition · Computer Science 2022-12-29 Fangcheng Liu , Chao Zhang , Hongyang Zhang

Adversarial examples' (AE) transferability refers to the phenomenon that AEs crafted with one surrogate model can also fool other models. Notwithstanding remarkable progress in untargeted transferability, its targeted counterpart remains…

Computer Vision and Pattern Recognition · Computer Science 2025-01-03 Hui Zeng , Sanshuai Cui , Biwei Chen , Anjie Peng

Deep neural networks are vulnerable to adversarial examples that are crafted by imposing imperceptible changes to the inputs. However, these adversarial examples are most successful in white-box settings where the model and its parameters…

Machine Learning · Computer Science 2021-12-20 Tianjin Huang , Vlado Menkovski , Yulong Pei , YuHao Wang , Mykola Pechenizkiy

It is widely recognized that deep learning models lack robustness to adversarial examples. An intriguing property of adversarial examples is that they can transfer across different models, which enables black-box attacks without any…

Computer Vision and Pattern Recognition · Computer Science 2024-03-05 Huanran Chen , Yichi Zhang , Yinpeng Dong , Xiao Yang , Hang Su , Jun Zhu

Adversarial examples (AE) with good transferability enable practical black-box attacks on diverse target models, where insider knowledge about the target models is not required. Previous methods often generate AE with no or very limited…

Machine Learning · Computer Science 2023-07-11 Tao Wu , Tie Luo , Donald C. Wunsch

We consider the black-box adversarial setting, where the adversary has to generate adversarial perturbations without access to the target models to compute gradients. Previous methods tried to approximate the gradient either by using a…

Machine Learning · Computer Science 2020-07-28 Shuyu Cheng , Yinpeng Dong , Tianyu Pang , Hang Su , Jun Zhu

The vulnerability of deep neural networks (DNNs) to black-box adversarial attacks is one of the most heated topics in trustworthy AI. In such attacks, the attackers operate without any insider knowledge of the model, making the cross-model…

Machine Learning · Computer Science 2025-01-08 Mingyuan Fan , Cen Chen , Wenmeng Zhou , Yinggui Wang

Deep neural networks are vulnerable to adversarial examples, which are crafted by adding small, human-imperceptible perturbations to the original images, but make the model output inaccurate predictions. Before deep neural networks are…

Computer Vision and Pattern Recognition · Computer Science 2021-01-13 Bo Yang , Kaiyong Xu , Hengjun Wang , Hengwei Zhang

Adversarial attacks can mislead deep neural networks (DNNs) by adding imperceptible perturbations to benign examples. The attack transferability enables adversarial examples to attack black-box DNNs with unknown architectures or parameters,…

Computer Vision and Pattern Recognition · Computer Science 2023-04-25 Kaisheng Liang , Bin Xiao

As deep neural networks (DNNs) are widely applied in the physical world, many researches are focusing on physical-world adversarial examples (PAEs), which introduce perturbations to inputs and cause the model's incorrect outputs. However,…

Computer Vision and Pattern Recognition · Computer Science 2024-12-24 Yichen Wang , Yuxuan Chou , Ziqi Zhou , Hangtao Zhang , Wei Wan , Shengshan Hu , Minghui Li

The transferability of adversarial examples allows for the attack on unknown deep neural networks (DNNs), posing a serious threat to many applications and attracting great attention. In this paper, we improve the transferability of…

Machine Learning · Computer Science 2025-10-16 Qizhang Li , Yiwen Guo , Xiaochen Yang , Wangmeng Zuo , Hao Chen

Adversarial attacks are a central tool for probing the robustness of modern vision models, yet most methods optimize perturbations directly in pixel space under $\ell_\infty$ or $\ell_2$ constraints. While effective in white-box settings,…

Computer Vision and Pattern Recognition · Computer Science 2026-03-09 Eitan Shaar , Ariel Shaulov , Yalcin Tur , Gal Chechik , Ravid Shwartz-Ziv

Adversarial attacks with improved transferability - the ability of an adversarial example crafted on a known model to also fool unknown models - have recently received much attention due to their practicality. Nevertheless, existing…

Computer Vision and Pattern Recognition · Computer Science 2022-12-05 Woo Jae Kim , Seunghoon Hong , Sung-Eui Yoon

Deep neural networks are vulnerable to adversarial examples, which can fool deep models by adding subtle perturbations. Although existing attacks have achieved promising results, it still leaves a long way to go for generating transferable…

Computer Vision and Pattern Recognition · Computer Science 2022-01-04 Yexin Duan , Junhua Zou , Xingyu Zhou , Wu Zhang , Jin Zhang , Zhisong Pan