On the robustness of randomized classifiers to adversarial examples

DOI10.1007/S10994-022-06216-6MaRDI QIDQ2102396zbMATH OpenOpenAlexFDO

Authors Rafaël Pinot, Laurent Meunier, Florian Yger, Cédric Gouy-Pailler, Yann Chevaleyre, Jamal Atif

Publication date 28 November 2022

Published in Machine Learning (Search for Journal in Brave)

Copyright license Creative Commons Attribution 4.0 International

Full work available at URL https://arxiv.org/abs/2102.10875

zbMATH Keywords

information theoryadversarial examplesrandomized smoothingadversarial generalization gaprandomized classifier

Mathematics Subject Classification ID

Learning and adaptive systems in artificial intelligence (68T05)

Cites work

• scientific article; zbMATH DE number 3173999 (Why is no real title available?)
• scientific article; zbMATH DE number 107482 (Why is no real title available?)
• scientific article; zbMATH DE number 1909499 (Why is no real title available?)
• 10.1162/153244303321897690
• Asymptotic Statistics
• Computational optimal transport. With applications to data sciences
• Foundations of machine learning
• GGHLite: more efficient multilinear maps from ideal lattices
• Learning in the Presence of Malicious Errors
• Noise-Enhanced Performance for an Optimal Bayesian Estimator
• Note on discrimination information and variation (Corresp.)
• On Choosing and Bounding Probability Metrics
• On Pinsker's and Vajda's Type Inequalities for Csiszár's $f$-Divergences
• Robust optimization
• Robustness and generalization
• Rényi Divergence and Kullback-Leibler Divergence
• Stochastic resonance in discrete time nonlinear AR(1) models.
• The Bayesian Choice
• Toward efficient agnostic learning
• Understanding machine learning. From theory to algorithms

Cited in

(3)

• Analysis of classifiers' robustness to adversarial perturbations
• Robust Classification Under $\ell_0$ Attack for the Gaussian Mixture Model
• On biased random walks, corrupted intervals, and learning under adversarial design

Describes a project that uses

Uses Software

• CIFAR

This page was built for publication: On the robustness of randomized classifiers to adversarial examples

Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q2102396)