Theoretical evidence for adversarial robustness through randomization: the case of the Exponential family

By Rafael Pinot, Laurent Meunier, Alexandre Araujo, Hisashi Kashima, Florian Yger, Cédric Gouy-Pailler, Jamal Atif. 2019

91 citations recorded by the source corpus.

This paper investigates the theory of robustness against adversarial attacks. It focuses on the family of randomization techniques that consist in injecting noise in the network at inference time. These techniques have proven effective in many contexts, but lack theoretical arguments. We close this gap by presenting a theoretical analysis of these approaches, hence explaining why they perform well in practice. More precisely, we provide the first result relating the randomization rate to robustness to adversarial attacks. This result applies for the general family of exponential distributions, and thus extends and unifies the previous approaches. We support our theoretical claims with a set of experiments.

Subfields: Artificial Intelligence, Safety, Robustness & Interpretability, Statistical Learning Theory

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

In Safety, Robustness & Interpretability

In Statistical Learning Theory

Citations in the corpus

A Closer Look at Accuracy vs. Robustness (2020, background): “Many works consider a randomized notion of local smoothness, and they prove that enforcing it can lead to certifiably robust classifiers [27, 10, 37, 46].”