Zobrazeno 1 - 7
of 7
pro vyhledávání: '"Goibert, Morgane"'
As the issue of robustness in AI systems becomes vital, statistical learning techniques that are reliable even in presence of partly contaminated data have to be developed. Preference data, in the form of (complete) rankings in the simplest situation
Externí odkaz:
http://arxiv.org/abs/2303.12878
In this paper, we investigate the impact of neural networks (NNs) topology on adversarial robustness. Specifically, we study the graph produced when an input traverses all the layers of a NN, and show that such graphs are different for clean and adve
Externí odkaz:
http://arxiv.org/abs/2211.02675
In this paper, we initiate a rigorous study of the phenomenon of low-dimensional adversarial perturbations (LDAPs) in classification. Unlike the classical setting, these perturbations are limited to a subspace of dimension $k$ which is much smaller t
Externí odkaz:
http://arxiv.org/abs/2203.13779
The concept of median/consensus has been widely investigated in order to provide a statistical summary of ranking data, i.e. realizations of a random permutation $\Sigma$ of a finite set, $\{1,\; \ldots,\; n\}$ with $n\geq 1$ say. As it sheds light o
Externí odkaz:
http://arxiv.org/abs/2201.08105
Autor:
Goibert, Morgane, Dohmatob, Elvis
We study Label-Smoothing as a means for improving adversarial robustness of supervised deep-learning models. After establishing a thorough and unified framework, we propose several variations to this general method: adversarial, Boltzmann and second-
Externí odkaz:
http://arxiv.org/abs/1906.11567
Autor:
Goibert, Morgane, Dohmatob, Elvis
We study Label-Smoothing as a means for improving adversarial robustness of supervised deep-learning models. After establishing a thorough and unified framework, we propose several variations to this general method: adversarial, Boltzmann and second-
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=dedup_wf_001::90f1128098241115570faf3614495366
https://hal.archives-ouvertes.fr/hal-02437752
https://hal.archives-ouvertes.fr/hal-02437752
Autor:
Goibert, Morgane, Dohmatob, Elvis
We study Label-Smoothing as a means for improving adversarial robustness of supervised deep-learning models. After establishing a thorough and unified framework, we propose several variations to this general method: adversarial, Boltzmann and second-
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::821445008395e69bce3b5349300e556a