The coupling effect of Lipschitz regularization in deep neural networks

With the increasing interest in deep neural networks, a lot of research work has been focusing lately on their sensitivity to input perturbations [3, 12, 8, 11]. Most of these investigations have highlighted their weakness to handle adversarial attacks and the addressed means to increase their robustness. Adversarial attacks are real threats that could slow down or eventually stop the development and applications of these tools wherever robustness guarantees are needed. If input uncertainty is not adversarial but simply generated by the context and environment of the specific application, deep networks do not show better behavior in terms of robustness. If no immunization mechanism is used, their generalization performance can greatly suffer.