← Search

Renkun Ni*

1 accepted papers

2020

Certified Defenses for Adversarial Patches

ICLR 2020poster

Adversarial patch attacks are among one of the most practical threat models against real-world computer vision systems. This paper studies certified and empirical defenses against patch attacks. We begin with a set of experiments showing that most existing defenses, which work by pre-processing inpu…

Cited by 198SourcecodeScholar