most citedTheoretical evidence for adversarial robustness through randomization

35 citations · 35 across the 1 of their papers we have counts for

collaborators

6 papers

cs.LG2020

Advocating for Multiple Defense Strategies against Adversarial Examples

Alexandre Araujo, Laurent Meunier, Rafael Pinot +1

It has been empirically observed that defense mechanisms designed to protect neural networks against adversarial examples offer poor performance against adve…

cs.LG2020

On Lipschitz Regularization of Convolutional Layers using Toeplitz Matrix Theory

Alexandre Araujo, Benjamin Negrevergne, Yann Chevaleyre +1

This paper tackles the problem of Lipschitz regularization of Convolutional Neural Networks. Lipschitz regularity is now established as a key property of modern deep learning with…

cs.LG2019

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.LG201935 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…

cs.LG2019

Understanding and Training Deep Diagonal Circulant Neural Networks

Alexandre Araujo, Benjamin Negrevergne, Yann Chevaleyre +1

In this paper, we study deep diagonal circulant neural networks, that is deep neural networks in which weight matrices are the product of diagonal and circulant ones. Besides makin…

cs.CV2018

Training compact deep learning models for video classification using circulant matrices

Alexandre Araujo, Benjamin Negrevergne, Yann Chevaleyre +1

In real world scenarios, model accuracy is hardly the only factor to consider. Large models consume more memory and are computationally more intensive, which makes them difficult t…