Publications
Detailed Information
Parsimonious black-box adversarial attacks via efficient combinatorial optimization
Cited 0 time in
Web of Science
Cited 29 time in Scopus
- Authors
- Issue Date
- 2019-01
- Citation
- 36th International Conference on Machine Learning, ICML 2019, Vol.2019-June, pp.8149-8158
- Abstract
- © 2019 by the author(s).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.
- Files in This Item:
- There are no files associated with this item.
Item View & Download Count
Items in S-Space are protected by copyright, with all rights reserved, unless otherwise indicated.