Robustness of classifiers to uniform 𝓁p and Gaussian noise

31 citations recorded by the source corpus.

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

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).”
Robust sound event detection in bioacoustic sensor networks (2019, background): “On the contrary, as described in the Methods section, PCEN tends to bring the distribution of background time-frequency magnitudes closer to additive white Gaussian noise (AWGN).”
Does Data Augmentation Lead to Positive Margin? (2019, background): “Franceschi et al. (2018) provide a geometric characterization of the robustness of linear and “locally approximately ﬂat” classiﬁers.”
On the Geometry of Adversarial Examples (2018, methodology): “We consider two attacks, the fast gradient sign method (FGSM) (Goodfellow et al. (2014)) and the basic iterative method (BIM) (Kurakin et al. (2016)) under ‖·‖2.”