papers AI Learner
The Github is limit! Click to go to the new site.

Parsimonious Black-Box Adversarial Attacks via Efficient Combinatorial Optimization

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

Abstract

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.

Abstract (translated by Google)
URL

http://arxiv.org/abs/1905.06635

PDF

http://arxiv.org/pdf/1905.06635


Similar Posts

Comments