English

Bayesian Adversarial Spheres: Bayesian Inference and Adversarial Examples in a Noiseless Setting

Machine Learning 2018-11-30 v1 Machine Learning

Abstract

Modern deep neural network models suffer from adversarial examples, i.e. confidently misclassified points in the input space. It has been shown that Bayesian neural networks are a promising approach for detecting adversarial points, but careful analysis is problematic due to the complexity of these models. Recently Gilmer et al. (2018) introduced adversarial spheres, a toy set-up that simplifies both practical and theoretical analysis of the problem. In this work, we use the adversarial sphere set-up to understand the properties of approximate Bayesian inference methods for a linear model in a noiseless setting. We compare predictions of Bayesian and non-Bayesian methods, showcasing the advantages of the former, although revealing open challenges for deep learning applications.

Keywords

Cite

@article{arxiv.1811.12335,
  title  = {Bayesian Adversarial Spheres: Bayesian Inference and Adversarial Examples in a Noiseless Setting},
  author = {Artur Bekasov and Iain Murray},
  journal= {arXiv preprint arXiv:1811.12335},
  year   = {2018}
}

Comments

To appear in the third workshop on Bayesian Deep Learning (NeurIPS 2018), Montreal, Canada

R2 v1 2026-06-23T06:25:37.990Z