Parsimonious Black-Box Adversarial Attacks via Efficient Combinatorial Optimization
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.
Code (1)
Tasks
Combinatorial OptimizationSimilar Papers 제목 키워드 기반
Black-box Adversarial Attacks with Bayesian Optimization
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 OptimizationAttacking Graph Classification via Bayesian Optimisation
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 ClassificationSimple and Efficient Hard Label Black-box Adversarial Attacks in Low Query Budget Regimes
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 OptimizationAdversarial Attacks on Graph Classifiers via Bayesian Optimisation
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 ClassificationAdversarial Attacks on Graph Classification via Bayesian Optimisation
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