Adversarially Robust Training through Structured Gradient Regularization

05/22/2018 ∙ by Kevin Roth, et al. ∙ 2

We propose a novel data-dependent structured gradient regularizer to increase the robustness of neural networks vis-a-vis adversarial perturbations. Our regularizer can be derived as a controlled approximation from first principles, leveraging the fundamental link between training with noise and regularization. It adds very little computational overhead during learning and is simple to implement generically in standard deep learning frameworks. Our experiments provide strong evidence that structured gradient regularization can act as an effective first line of defense against attacks based on low-level signal corruption.

READ FULL TEXT
POST COMMENT

Comments

There are no comments yet.

Authors

page 16

This week in AI

Get the week's most popular data science and artificial intelligence research sent straight to your inbox every Saturday.