Adversarial Consistency and the Uniqueness of the Adversarial Bayes Classifier
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.
Code (0)
등록된 구현이 없습니다.
Tasks
ClassificationSimilar Papers 제목 키워드 기반
A Notion of Uniqueness for the Adversarial Bayes Classifier
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 ClassificationOn the Existence of The Adversarial Bayes Classifier
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 RobustnessOn the Existence of the Adversarial Bayes Classifier (Extended Version)
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 RobustnessOn existence, uniqueness and scalability of adversarial robustness measures for AI classifiers
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 RobustnessA Bayes-Optimal View on Adversarial Examples
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