English

Black-box Certification and Learning under Adversarial Perturbations

Machine Learning 2022-02-23 v2 Machine Learning

Abstract

We formally study the problem of classification under adversarial perturbations from a learner's perspective as well as a third-party who aims at certifying the robustness of a given black-box classifier. We analyze a PAC-type framework of semi-supervised learning and identify possibility and impossibility results for proper learning of VC-classes in this setting. We further introduce a new setting of black-box certification under limited query budget, and analyze this for various classes of predictors and perturbation. We also consider the viewpoint of a black-box adversary that aims at finding adversarial examples, showing that the existence of an adversary with polynomial query complexity can imply the existence of a sample efficient robust learner.

Keywords

Cite

@article{arxiv.2006.16520,
  title  = {Black-box Certification and Learning under Adversarial Perturbations},
  author = {Hassan Ashtiani and Vinayak Pathak and Ruth Urner},
  journal= {arXiv preprint arXiv:2006.16520},
  year   = {2022}
}
R2 v1 2026-06-23T16:43:24.695Z