40 citations · 159 across the 15 of their papers we have counts for
10 papers · 1 filter
On the Role of Randomization in Adversarially Robust Classification
Lucas Gnecco-Heredia, Yann Chevaleyre, Benjamin Negrevergne +2
Deep neural networks are known to be vulnerable to small adversarial perturbations in test data. To defend against adversarial attacks, probabilistic classifiers have been proposed…
Towards Consistency in Adversarial Classification
Laurent Meunier, Raphaël Ettedgui, Rafael Pinot +2
In this paper, we study the problem of consistency in the context of adversarial examples. Specifically, we tackle the following question: can surrogate losses still be used as a p…
A Dynamical System Perspective for Lipschitz Neural Networks
Laurent Meunier, Blaise Delattre, Alexandre Araujo +1
The Lipschitz constant of neural networks has been established as a key quantity to enforce the robustness to adversarial examples. In this paper, we tackle the problem of building…
On the robustness of randomized classifiers to adversarial examples
Rafael Pinot, Laurent Meunier, Florian Yger +3
This paper investigates the theory of robustness against adversarial attacks. We focus on randomized classifiers (\emph{i.e.} classifiers that output random variables) and provide…
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…
Black-Box Optimization Revisited: Improving Algorithm Selection Wizards through Massive Benchmarking
Laurent Meunier, Herilalaina Rakotoarison, Pak Kan Wong +5
Existing studies in black-box optimization for machine learning suffer from low generalizability, caused by a typically selective choice of problem instances used for training and…
Adversarial Attacks on Linear Contextual Bandits
Evrard Garcelon, Baptiste Roziere, Laurent Meunier +4
Contextual bandit algorithms are applied in a wide range of domains, from advertising to recommender systems, from clinical trials to education. In many of these domains, malicious…
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…
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…
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…