paper-with-me

홈 › Papers

Adversarial Consistency and the Uniqueness of the Adversarial Bayes Classifier

2024-04-26 · Natalie S. Frank

Minimizing an adversarial surrogate risk is a common technique for learning robust classifiers. Prior work showed that convex surrogate losses are not statistically consistent in the adversarial context -- or in other words, a minimizing sequence of the adversarial surrogate risk will not necessarily minimize the adversarial classification error. We connect the consistency of adversarial surrogate losses to properties of minimizers to the adversarial classification risk, known as adversarial Bayes classifiers. Specifically, under reasonable distributional assumptions, a convex surrogate loss is statistically consistent for adversarial learning iff the adversarial Bayes classifier satisfies a certain notion of uniqueness.

📄 PDF Abstract BibTeX arXiv:2404.17358

Code (0)

등록된 구현이 없습니다.

Tasks

Classification

Similar Papers 제목 키워드 기반

A Notion of Uniqueness for the Adversarial Bayes Classifier

2024-04-25 · Natalie S. Frank

We propose a new notion of uniqueness for the adversarial Bayes classifier in the setting of binary classification. Analyzing this concept produces a simple procedure for computing all adversarial Bayes classifiers for a…

Binary Classification

On the Existence of The Adversarial Bayes Classifier

2021-12-01 · NeurIPS 2021 12 · Pranjal Awasthi, Natalie Frank, Mehryar Mohri

Adversarial robustness is a critical property in a variety of modern machine learning applications. While it has been the subject of several recent theoretical studies, many important questions related to adversarial rob…

Adversarial Robustness

On the Existence of the Adversarial Bayes Classifier (Extended Version)

2021-12-03 · Pranjal Awasthi, Natalie S. Frank, Mehryar Mohri

Adversarial robustness is a critical property in a variety of modern machine learning applications. While it has been the subject of several recent theoretical studies, many important questions related to adversarial rob…

Adversarial Robustness

On existence, uniqueness and scalability of adversarial robustness measures for AI classifiers

2023-10-19 · Illia Horenko

Simply-verifiable mathematical conditions for existence, uniqueness and explicit analytical computation of minimal adversarial paths (MAP) and minimal adversarial distances (MAD) for (locally) uniquely-invertible classif…

Adversarial Robustness

A Bayes-Optimal View on Adversarial Examples

2020-02-20 · Eitan Richardson, Yair Weiss

Since the discovery of adversarial examples - the ability to fool modern CNN classifiers with tiny perturbations of the input, there has been much discussion whether they are a "bug" that is specific to current neural ar…

Adversarial Attack