Persistent Classification: A New Approach to Stability of Data and Adversarial Examples

arXiv:2404.08069v1 Announce Type: new
Abstract: There are a number of hypotheses underlying the existence of adversarial examples for classification problems. These include the high-dimensionality of the data, high codimension in the ambient space of the data manifolds of interest, and that the structure of machine learning models may encourage classifiers to develop decision boundaries close to data points. This article proposes a new framework for studying adversarial examples that does not depend directly on the distance to the decision boundary. …

abstract adversarial adversarial examples ambient arxiv classification cs.lg data dimensionality examples machine machine learning machine learning models space stability type