English
Related papers

Related papers: SurFree: a fast surrogate-free black-box attack

200 papers

Decision-based evasion attacks repeatedly query a black-box classifier to generate adversarial examples. Prior work measures the cost of such attacks by the total number of queries made to the classifier. We argue this metric is flawed.…

Cryptography and Security · Computer Science 2024-02-15 Edoardo Debenedetti , Nicholas Carlini , Florian Tramèr

A recent line of work on black-box adversarial attacks has revived the use of transfer from surrogate models by integrating it into query-based search. However, we find that existing approaches of this type underperform their potential, and…

Machine Learning · Computer Science 2022-03-17 Nicholas A. Lord , Romain Mueller , Luca Bertinetto

Solving for adversarial examples with projected gradient descent has been demonstrated to be highly effective in fooling the neural network based classifiers. However, in the black-box setting, the attacker is limited only to the query…

Machine Learning · Computer Science 2022-10-19 Seungyong Moon , Gaon An , Hyun Oh Song

This paper addresses the challenging black-box adversarial attack problem, where only classification confidence of a victim model is available. Inspired by consistency of visual saliency between different vision models, a surrogate model is…

Cryptography and Security · Computer Science 2020-10-23 Jiancheng Yang , Yangzhou Jiang , Xiaoyang Huang , Bingbing Ni , Chenglong Zhao

We study black-box attacks on machine learning classifiers where each query to the model incurs some cost or risk of detection to the adversary. We focus explicitly on minimizing the number of queries as a major objective. Specifically, we…

Cryptography and Security · Computer Science 2017-12-27 Fnu Suya , Yuan Tian , David Evans , Paolo Papotti

Unlike the white-box counterparts that are widely studied and readily accessible, adversarial examples in black-box settings are generally more Herculean on account of the difficulty of estimating gradients. Many methods achieve the task by…

Computer Vision and Pattern Recognition · Computer Science 2019-06-12 Ziang Yan , Yiwen Guo , Changshui Zhang

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

Adversarial attacks have been extensively studied in recent years since they can identify the vulnerability of deep learning models before deployed. In this paper, we consider the black-box adversarial setting, where the adversary needs to…

Machine Learning · Computer Science 2022-03-15 Yinpeng Dong , Shuyu Cheng , Tianyu Pang , Hang Su , Jun Zhu

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,…

Computer Vision and Pattern Recognition · Computer Science 2025-06-03 Md Farhamdur Reza , Richeng Jin , Tianfu Wu , Huaiyu Dai

Many adversarial attack approaches are proposed to verify the vulnerability of language models. However, they require numerous queries and the information on the target model. Even black-box attack methods also require the target model's…

Cryptography and Security · Computer Science 2025-04-21 CheolWon Na , YunSeok Choi , Jee-Hyong Lee

Adversarial examples are known as carefully perturbed images fooling image classifiers. We propose a geometric framework to generate adversarial examples in one of the most challenging black-box settings where the adversary can only…

Computer Vision and Pattern Recognition · Computer Science 2020-03-17 Ali Rahmati , Seyed-Mohsen Moosavi-Dezfooli , Pascal Frossard , Huaiyu Dai

We study the problem of attacking a machine learning model in the hard-label black-box setting, where no model information is revealed except that the attacker can make queries to probe the corresponding hard-label decisions. This is a very…

Machine Learning · Computer Science 2018-07-13 Minhao Cheng , Thong Le , Pin-Yu Chen , Jinfeng Yi , Huan Zhang , Cho-Jui Hsieh

Traditional decision-based black-box adversarial attacks on image classifiers aim to generate adversarial examples by slightly modifying input images while keeping the number of queries low, where each query involves sending an input to the…

Machine Learning · Computer Science 2025-06-10 Mahdi Salmani , Alireza Abdollahpoorrostam , Seyed-Mohsen Moosavi-Dezfooli

We consider the hard label based black box adversarial attack setting which solely observes predicted classes from the target model. Most of the attack methods in this setting suffer from impractical number of queries required to achieve a…

Machine Learning · Computer Science 2024-03-12 Jeonghwan Park , Paul Miller , Niall McLaughlin

Machine learning security has recently become a prominent topic in the natural language processing (NLP) area. The existing black-box adversarial attack suffers prohibitively from the high model querying complexity, resulting in easily…

Cryptography and Security · Computer Science 2023-10-17 Wenjie Lv , Zhen Wang , Yitao Zheng , Zhehua Zhong , Qi Xuan , Tianyi Chen

Despite our best efforts, deep learning models remain highly vulnerable to even tiny adversarial perturbations applied to the inputs. The ability to extract information from solely the output of a machine learning model to craft adversarial…

Machine Learning · Computer Science 2023-03-27 Viet Quoc Vo , Ehsan Abbasnejad , Damith C. Ranasinghe

Deep learning models are vulnerable to adversarial examples, which can fool a target classifier by imposing imperceptible perturbations onto natural examples. In this work, we consider the practical and challenging decision-based black-box…

Machine Learning · Computer Science 2021-05-11 Qi-An Fu , Yinpeng Dong , Hang Su , Jun Zhu

Decision-based black-box attacks often necessitate a large number of queries to craft an adversarial example. Moreover, decision-based attacks based on querying boundary points in the estimated normal vector direction often suffer from…

Computer Vision and Pattern Recognition · Computer Science 2023-08-08 Md Farhamdur Reza , Ali Rahmati , Tianfu Wu , Huaiyu Dai

Recent studies have highlighted that deep neural networks (DNNs) are vulnerable to adversarial attacks, even in a black-box scenario. However, most of the existing black-box attack algorithms need to make a huge amount of queries to perform…

Machine Learning · Statistics 2018-09-11 Yali Du , Meng Fang , Jinfeng Yi , Jun Cheng , Dacheng Tao

One of the most practical and challenging types of black-box adversarial attacks is the hard-label attack, where only the top-1 predicted label is available. One effective approach is to search for the optimal ray direction from the benign…

Computer Vision and Pattern Recognition · Computer Science 2025-07-24 Chen Ma , Xinjie Xu , Shuyu Cheng , Qi Xuan
‹ Prev 1 2 3 10 Next ›