Uniform convergence of adversarially robust classifiers

DOI10.1017/S0956792525100223MaRDI QIDQ6877261zbMATH OpenFDO

Authors Rachel Morris, Ryan W. Murray

Publication date 8 January 2026

Published in European Journal of Applied Mathematics (Search for Journal in Brave)

Copyright license Creative Commons Attribution 4.0 International

Full work available at URL https://doi.org/10.1017/S0956792525100223

zbMATH Keywords

adversarial traininggeometric measure theoryHausdorff convergencerobust classification

Mathematics Subject Classification ID

Length, area, volume, other geometric measure theory (28A75) Singular perturbations in context of PDEs (35B25) Nonparametric robustness (62G35) Classification and discrimination; cluster analysis (statistical aspects) (62H30)

Cites work

• A mean curvature flow arising in adversarial training
• Adversarial Risk via Optimal Transport and Optimal Couplings
• Gamma-convergence of a nonlocal perimeter arising in adversarial machine learning
• Isoperimetric problems for a nonlocal perimeter of Minkowski type
• Minimizers for nonlocal perimeters of Minkowski type
• Nonlocal curvature flows
• The geometry of adversarial training in binary classification
• The many faces of adversarial risk: an expanded study

This page was built for publication: Uniform convergence of adversarially robust classifiers

Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q6877261)