activity
20182023
most citedTheoretical evidence for adversarial robustness through randomization

35 citations · 60 across the 10 of their papers we have counts for

collaborators
Showing cs.LGShow all

9 papers · 1 filter

cs.LG2023

The Lipschitz-Variance-Margin Tradeoff for Enhanced Randomized Smoothing

Blaise Delattre, Alexandre Araujo, Quentin Barthélemy +1

Real-life applications of deep neural networks are hindered by their unsteady predictions when faced with noisy inputs and adversarial attacks. The certified radius in this context…

cs.LG2023

Efficient Bound of Lipschitz Constant for Convolutional Layers by Gram Iteration

Blaise Delattre, Quentin Barthélemy, Alexandre Araujo +1

Since the control of the Lipschitz constant has a great impact on the training stability, generalization, and robustness of neural networks, the estimation of this value is nowaday…

cs.LG2023★ 1 cited

A Unified Algebraic Perspective on Lipschitz Neural Networks

Alexandre Araujo, Aaron Havens, Blaise Delattre +2

Important research efforts have focused on the design and training of neural networks with a controlled Lipschitz constant. The goal is to increase and sometimes guarantee the robu…

cs.LG2021★ 1 cited

Building Compact and Robust Deep Neural Networks with Toeplitz Matrices

Alexandre Araujo

Deep neural networks are state-of-the-art in a wide variety of tasks, however, they exhibit important limitations which hinder their use and deployment in real-world applications.…

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…