Search Results for author: Raphael Ettedgui

Found 3 papers, 1 papers with code

Randomization matters How to defend against strong adversarial attacks

no code implementations ICML 2020 Rafael Pinot, Raphael Ettedgui, Geovani Rizk, Yann Chevaleyre, Jamal Atif

We demonstrate the non-existence of a Nash equilibrium in our game when the classifier and the adversary are both deterministic, hence giving a negative answer to the above question in the deterministic regime.

Towards Evading the Limits of Randomized Smoothing: A Theoretical Analysis

no code implementations3 Jun 2022 Raphael Ettedgui, Alexandre Araujo, Rafael Pinot, Yann Chevaleyre, Jamal Atif

We first show that these certificates use too little information about the classifier, and are in particular blind to the local curvature of the decision boundary.

Randomization matters. How to defend against strong adversarial attacks

1 code implementation26 Feb 2020 Rafael Pinot, Raphael Ettedgui, Geovani Rizk, Yann Chevaleyre, Jamal Atif

We demonstrate the non-existence of a Nash equilibrium in our game when the classifier and the Adversary are both deterministic, hence giving a negative answer to the above question in the deterministic regime.

Cannot find the paper you are looking for? You can Submit a new open access paper.