Lipschitz regularized Deep Neural Networks generalize and are adversarially robust [article]

Chris Finlay, Jeff Calder, Bilal Abbasi, Adam Oberman
2019 arXiv   pre-print
In this work we study input gradient regularization of deep neural networks, and demonstrate that such regularization leads to generalization proofs and improved adversarial robustness. The proof of generalization does not overcome the curse of dimensionality, but it is independent of the number of layers in the networks. The adversarial robustness regularization combines adversarial training, which we show to be equivalent to Total Variation regularization, with Lipschitz regularization. We
more » ... onstrate empirically that the regularized models are more robust, and that gradient norms of images can be used for attack detection.
arXiv:1808.09540v4 fatcat:dzdm4ubljja4jntxju6xzyql5m