paper-with-me

홈 › Papers

Parsimonious Black-Box Adversarial Attacks via Efficient Combinatorial Optimization

2019-05-16 · Seungyong Moon, Gaon An, Hyun Oh Song

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 access to the network and solving for a successful adversarial example becomes much more difficult. To this end, recent methods aim at estimating the true gradient signal based on the input queries but at the cost of excessive queries. We propose an efficient discrete surrogate to the optimization problem which does not require estimating the gradient and consequently becomes free of the first order update hyperparameters to tune. Our experiments on Cifar-10 and ImageNet show the state of the art black-box attack performance with significant reduction in the required queries compared to a number of recently proposed methods. The source code is available at https://github.com/snu-mllab/parsimonious-blackbox-attack.

📄 PDF Abstract BibTeX arXiv:1905.06635

Code (1)

snu-mllab/parsimonious-blackbox-attack 공식 구현 tf

Tasks

Combinatorial Optimization

Similar Papers 제목 키워드 기반

Black-box Adversarial Attacks with Bayesian Optimization

2019-09-30 · Satya Narayan Shukla, Anit Kumar Sahu, Devin Willmott, J. Zico Kolter

We focus on the problem of black-box adversarial attacks, where the aim is to generate adversarial examples using information limited to loss function evaluations of input-output pairs. We use Bayesian optimization~(BO) …

Bayesian Optimization

Attacking Graph Classification via Bayesian Optimisation

2021-06-18 · ICML Workshop AML 2021 7 · Xingchen Wan, Henry Kenlay, Binxin Ru, Arno Blaas 외

Graph neural networks have been shown to be vulnerable to adversarial attacks. While the majority of the literature focuses on such vulnerability in node-level classification tasks, little effort has been dedicated to at…

Adversarial RobustnessBayesian OptimisationClassificationGraph Classification

Simple and Efficient Hard Label Black-box Adversarial Attacks in Low Query Budget Regimes

2020-07-13 · Satya Narayan Shukla, Anit Kumar Sahu, Devin Willmott, J. Zico Kolter

We focus on the problem of black-box adversarial attacks, where the aim is to generate adversarial examples for deep learning models solely based on information limited to output label~(hard label) to a queried data inpu…

Bayesian Optimization

Adversarial Attacks on Graph Classifiers via Bayesian Optimisation

2021-12-01 · NeurIPS 2021 12 · Xingchen Wan, Henry Kenlay, Robin Ru, Arno Blaas 외

Graph neural networks, a popular class of models effective in a wide range of graph-based learning tasks, have been shown to be vulnerable to adversarial attacks. While the majority of the literature focuses on such vuln…

Adversarial RobustnessBayesian OptimisationClassificationGraph Classification

Adversarial Attacks on Graph Classification via Bayesian Optimisation

2021-11-04 · Xingchen Wan, Henry Kenlay, Binxin Ru, Arno Blaas 외

Graph neural networks, a popular class of models effective in a wide range of graph-based learning tasks, have been shown to be vulnerable to adversarial attacks. While the majority of the literature focuses on such vuln…

Adversarial RobustnessBayesian OptimisationClassificationGraph Classification