Robustness of classifiers to uniform $\ell_p$ and Gaussian noise - Archive ouverte HAL Access content directly
Conference Papers Year : 2018

Robustness of classifiers to uniform $\ell_p$ and Gaussian noise


We study the robustness of classifiers to various kinds of random noise models. In particular, we consider noise drawn uniformly from the $\ell_p$ ball for $p \in [1, \infty]$ and Gaussian noise with an arbitrary covariance matrix. We characterize this robustness to random noise in terms of the distance to the decision boundary of the classifier. This analysis applies to linear classifiers as well as classifiers with locally approximately flat decision boundaries, a condition which is satisfied by state-of-the-art deep neural networks. The predicted robustness is verified experimentally.
Fichier principal
Vignette du fichier
paper_robustness_lp_new.pdf (2.13 Mo) Télécharger le fichier
Origin : Files produced by the author(s)

Dates and versions

hal-01715012 , version 1 (22-02-2018)





Jean-Yves Franceschi, Alhussein Fawzi, Omar Fawzi. Robustness of classifiers to uniform $\ell_p$ and Gaussian noise. Twenty-first International Conference on Artificial Intelligence and Statistics, Apr 2018, Playa Blanca, Spain. pp.1280-1288. ⟨hal-01715012⟩
501 View
94 Download



Gmail Facebook Twitter LinkedIn More