Bayesian Adversarial Spheres: Bayesian Inference and Adversarial Examples in a Noiseless Setting
arXiv:1811.12335
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.
arXiv commentTo appear in the third workshop on Bayesian Deep Learning (NeurIPS 2018), Montreal, Canada
References in corpus (8)
- Obfuscated Gradients Give a False Sense of Security: Circumventing Defenses to Adversarial Examples
- Scalable Bayesian Optimization Using Deep Neural Networks
- Adversarial Examples, Uncertainty, and Transfer Testing Robustness in Gaussian Process Hybrid Deep Networks
- Dropout Inference in Bayesian Neural Networks with Alpha-divergences
- Adversarial Spheres
- Black Box Variational Inference
- Sufficient Conditions for Idealised Models to Have No Adversarial Examples: a Theoretical and Empirical Study with Bayesian Neural Networks
- Adversarial Phenomenon in the Eyes of Bayesian Deep Learning