40 citations · 159 across the 15 of their papers we have counts for
Showing 2019Show all
3 papers · 1 filter
cs.LG2019★ 20 cited
Yet another but more efficient black-box adversarial attack: tiling and evolution strategies
Laurent Meunier, Jamal Atif, Olivier Teytaud
We introduce a new black-box attack achieving state of the art performances. Our approach is based on a new objective function, borrowing ideas from -white box attacks…
cs.LG2019★ 25 cited
Robust Neural Networks using Randomized Adversarial Training
Alexandre Araujo, Laurent Meunier, Rafael Pinot +1
This paper tackles the problem of defending a neural network against adversarial attacks crafted with different norms (in particular and bounded adversarial…
cs.LG2019★ 35 cited
Theoretical evidence for adversarial robustness through randomization
Rafael Pinot, Laurent Meunier, Alexandre Araujo +4
This paper investigates the theory of robustness against adversarial attacks. It focuses on the family of randomization techniques that consist in injecting noise in the network at…