← Search

Simranjit Singh

1 accepted papers

2020

Sign-OPT: A Query-Efficient Hard-label Adversarial Attack

ICLR 2020poster

We study the most practical problem setup for evaluating adversarial robustness of a machine learning system with limited access: the hard-label black-box attack setting for generating adversarial examples, where limited model queries are allowed and only the decision is provided to a queried data…

Cited by 305SourcecodeScholar