Zobrazeno 1 - 10
of 215
pro vyhledávání: '"Meunier, Laurent"'
Autor:
Gnecco-Heredia, Lucas, Chevaleyre, Yann, Negrevergne, Benjamin, Meunier, Laurent, Pydi, Muni Sreenivas
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 as an alternative to deterministic ones. However, literature has conf
Externí odkaz:
http://arxiv.org/abs/2302.07221
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 proxy for minimizing the $0/1$ loss in the presence of an adversary tha
Externí odkaz:
http://arxiv.org/abs/2205.10022
We propose a new conditional dependence measure and a statistical test for conditional independence. The measure is based on the difference between analytic kernel embeddings of two well-suited distributions evaluated at a finite set of locations. We
Externí odkaz:
http://arxiv.org/abs/2110.14868
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 $1$-Lipschitz Neural Networks. By studying Residual Networks from a c
Externí odkaz:
http://arxiv.org/abs/2110.12690
Parallel black box optimization consists in estimating the optimum of a function using $\lambda$ parallel evaluations of $f$. Averaging the $\mu$ best individuals among the $\lambda$ evaluations is known to provide better estimates of the optimum of
Externí odkaz:
http://arxiv.org/abs/2108.04707
Robustness to adversarial attacks is typically obtained through expensive adversarial training with Projected Gradient Descent. Here we introduce ROPUST, a remarkably simple and efficient method to leverage robust pre-trained models and further incre
Externí odkaz:
http://arxiv.org/abs/2108.04217
Autor:
Pinot, Rafael, Meunier, Laurent, Yger, Florian, Gouy-Pailler, Cédric, Chevaleyre, Yann, Atif, Jamal
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 a thorough analysis of their behavior through the lens of statistical
Externí odkaz:
http://arxiv.org/abs/2102.10875
This paper tackles the problem of adversarial examples from a game theoretic point of view. We study the open question of the existence of mixed Nash equilibria in the zero-sum game formed by the attacker and the classifier. While previous works usua
Externí odkaz:
http://arxiv.org/abs/2102.06905
Autor:
Cappelli, Alessandro, Ohana, Ruben, Launay, Julien, Meunier, Laurent, Poli, Iacopo, Krzakala, Florent
Publikováno v:
ICASSP 2022 - IEEE International Conference on Acoustics, Speech and Signal Processing
We propose a new defense mechanism against adversarial attacks inspired by an optical co-processor, providing robustness without compromising natural accuracy in both white-box and black-box settings. This hardware co-processor performs a nonlinear f
Externí odkaz:
http://arxiv.org/abs/2101.02115
It has been empirically observed that defense mechanisms designed to protect neural networks against $\ell_\infty$ adversarial examples offer poor performance against $\ell_2$ adversarial examples and vice versa. In this paper we conduct a geometrica
Externí odkaz:
http://arxiv.org/abs/2012.02632