CUED Publications database

Measuring Neural Net Robustness with Constraints

Bastani, O and Ioannou, Y and Lampropoulos, L and Vytiniotis, D and Nori, A and Criminisi, A (2016) Measuring Neural Net Robustness with Constraints. In: Neural Information Processing Systems, -- to --. (Unpublished)

Full text not available from this repository.


Despite having high accuracy, neural nets have been shown to be susceptible to adversarial examples, where a small perturbation to an input can cause it to become mislabeled. We propose metrics for measuring the robustness of a neural net and devise a novel algorithm for approximating these metrics based on an encoding of robustness as a linear program. We show how our metrics can be used to evaluate the robustness of deep neural nets with experiments on the MNIST and CIFAR-10 datasets. Our algorithm generates more informative estimates of robustness metrics compared to estimates based on existing algorithms. Furthermore, we show how existing approaches to improving robustness "overfit" to adversarial examples generated using a specific algorithm. Finally, we show that our techniques can be used to additionally improve neural net robustness both according to the metrics that we propose, but also according to previously proposed metrics.

Item Type: Conference or Workshop Item (UNSPECIFIED)
Uncontrolled Keywords: cs.LG cs.LG cs.CV cs.NE
Divisions: Div F > Machine Intelligence
Depositing User: Cron Job
Date Deposited: 17 Jul 2017 20:14
Last Modified: 14 Jun 2018 01:58