← Search

Thong Le

1 accepted papers

2019

Query-Efficient Hard-label Black-box Attack: An Optimization-based Approach

ICLR 2019poster

We study the problem of attacking machine learning models in the hard-label black-box setting, where no model information is revealed except that the attacker can make queries to probe the corresponding hard-label decisions. This is a very challenging problem since the direct extension of state-of-t…