DeepAI AI Chat
Log In Sign Up

On the existence of solutions to adversarial training in multiclass classification

04/28/2023
by   Nicolas Garcia Trillos, et al.
Purdue University
University of Wisconsin-Madison
0

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.

READ FULL TEXT

page 1

page 2

page 3

page 4

12/10/2018

Defending against Universal Perturbations with Shared Adversarial Training

Classifiers such as deep neural networks have been shown to be vulnerabl...
04/19/2021

Provable Robustness of Adversarial Training for Learning Halfspaces with Noise

We analyze the properties of adversarial training for learning adversari...
11/26/2021

The Geometry of Adversarial Training in Binary Classification

We establish an equivalence between a family of adversarial training pro...
06/17/2019

MixUp as Directional Adversarial Training

In this work, we explain the working mechanism of MixUp in terms of adve...
08/20/2018

Adversarial Removal of Demographic Attributes from Text Data

Recent advances in Representation Learning and Adversarial Training seem...
11/28/2022

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

In this paper we prove Gamma-convergence of a nonlocal perimeter of Mink...
06/18/2022

Existence and Minimax Theorems for Adversarial Surrogate Risks in Binary Classification

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