Robust Classification Under \ell₀ Attack for the Gaussian Mixture Model

DOI10.1137/21M1426286MaRDI QIDQ5070852zbMATH OpenOpenAlexFDO

Authors Payam Delgosha, Hamed Hassani, Ramtin Pedarsani

Publication date 14 April 2022

Published in SIAM Journal on Mathematics of Data Science (Search for Journal in Brave)

Full work available at URL https://arxiv.org/abs/2104.02189

zbMATH Keywords

adversarial learningrobust classificationsparse adversarial attacks

Mathematics Subject Classification ID

Computational learning theory (68Q32) Probability in computer science (algorithm analysis, random structures, phase transitions, etc.) (68Q87) General topics in artificial intelligence (68T01)

Recommendations

• Settling the robust learnability of mixtures of Gaussians
• Robustly learning mixtures of k arbitrary Gaussians
• On the robustness of randomized classifiers to adversarial examples
• Adversarial vulnerability bounds for Gaussian process classification
• A robust classification framework with mixture correntropy
• Analysis of classifiers' robustness to adversarial perturbations
• Robust supervised classification with mixture models: learning from data with uncertain labels
• Gaussian Mixture Models for Higher-Order Side Channel Analysis
• On the Adversarial Robustness of Robust Estimators

Cites work

• Adversarial Risk via Optimal Transport and Optimal Couplings

Cited in

(3)

• Precise statistical analysis of classification accuracies for adversarial training
• Giophantus distinguishing attack is a low dimensional learning with errors problem
• Adversarial vulnerability bounds for Gaussian process classification

This page was built for publication: Robust Classification Under $\ell_0$ Attack for the Gaussian Mixture Model

Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q5070852)