DeepAI AI Chat
Log In Sign Up

On the existence of solutions to adversarial training in multiclass classification

by   Nicolas Garcia Trillos, et al.
Purdue University
University of Wisconsin-Madison

We study three models of the problem of adversarial training in multiclass classification designed to construct robust classifiers against adversarial perturbations of data in the agnostic-classifier setting. We prove the existence of Borel measurable robust classifiers in each model and provide a unified perspective of the adversarial training problem, expanding the connections with optimal transport initiated by the authors in previous work and developing new connections between adversarial training in the multiclass setting and total variation regularization. As a corollary of our results, we prove the existence of Borel measurable solutions to the agnostic adversarial training problem in the binary classification setting, a result that improves results in the literature of adversarial training, where robust classifiers were only known to exist within the enlarged universal σ-algebra of the feature space.


page 1

page 2

page 3

page 4


Defending against Universal Perturbations with Shared Adversarial Training

Classifiers such as deep neural networks have been shown to be vulnerabl...

Provable Robustness of Adversarial Training for Learning Halfspaces with Noise

We analyze the properties of adversarial training for learning adversari...

The Geometry of Adversarial Training in Binary Classification

We establish an equivalence between a family of adversarial training pro...

MixUp as Directional Adversarial Training

In this work, we explain the working mechanism of MixUp in terms of adve...

Adversarial Removal of Demographic Attributes from Text Data

Recent advances in Representation Learning and Adversarial Training seem...

Gamma-convergence of a nonlocal perimeter arising in adversarial machine learning

In this paper we prove Gamma-convergence of a nonlocal perimeter of Mink...

Existence and Minimax Theorems for Adversarial Surrogate Risks in Binary Classification

Adversarial training is one of the most popular methods for training met...