A Dynamical System Perspective for Lipschitz Neural Networks

The Lipschitz constant of neural networks has been established as a key quantity to enforce the robustness to adversarial examples. In this paper, we tackle the problem of building -Lipschitz Neural Networks. By studying Residual Networks from a continuous time dynamical system perspective, we provide a generic method to build -Lipschitz Neural Networks and show that some previous approaches are special cases of this framework. Then, we extend this reasoning and show that ResNet flows derived from convex potentials define -Lipschitz transformations, that lead us to define the {\em Convex Potential Layer} (CPL). A comprehensive set of experiments on several datasets demonstrates the scalability of our architecture and the benefits as an -provable defense against adversarial examples.
View on arXiv