Laurent Meunier

Scalable Lipschitz Residual Networks with Convex Potential Flows

2021 · arXiv (Cornell University)

The Lipschitz constant of neural networks has been established as a key property to enforce the robustness of neural networks to adversarial examples. However, recent attempts to build $1$-Lipschitz Neural Networks have all shown limitations …

ADVERSARIAL ROBUSTNESS BY DESIGN THROUGH ANALOG COMPUTING AND SYNTHETIC GRADIENTS

2021 · arXiv (Cornell University)

We propose a new defense mechanism against adversarial attacks inspired by an optical co-processor, providing robustness without compromising natural accuracy in both white-box and black-box settings. This hardware co-processor performs a nonlinear fixed random transformation, …