Robustness of classifiers to uniform $\ell_p$ and Gaussian noise
By Jean-Yves Franceschi, Alhussein Fawzi, Omar Fawzi. 2018
21 citations recorded by the source corpus.
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.
Subfields: Artificial Intelligence
How researchers see this paper
The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.
In Artificial Intelligence
- J. Kolter
- Elan Rosenfeld
- Jeremy M. Cohen
- Matthias Hein
- Cho-Jui Hsieh
- Huan Zhang
- Maksym Andriushchenko
- Pieter Abbeel
Citations in the corpus
- Certified Adversarial Robustness via Randomized Smoothing (2019, methodology): “The robustness of neural networks to random noise has been analyzed both theoretically (Fawzi et al., 2016; Franceschi et al., 2018) and empirically (Dodge & Karam, 2017).”