Great advances in deep neural networks (DNNs) have led to state-of-the-art performance on
a wide range of tasks. However, recent studies have shown that DNNs are vulnerable to …

This paper introduces a new parameterization of deep neural networks (both fully-connected
and convolutional) with guaranteed $\ell^ 2$ Lipschitz bounds, ie limited sensitivity to input …

Important research efforts have focused on the design and training of neural networks with a
controlled Lipschitz constant. The goal is to increase and sometimes guarantee the …

The robustness of neural networks against input perturbations with bounded magnitude
represents a serious concern in the deployment of deep learning models in safety-critical …

Despite the promise of Lipschitz-based methods for provably-robust deep learning with
deterministic guarantees, current state-of-the-art results are limited to feed-forward …

Recently, semidefinite programming (SDP) techniques have shown great promise in
providing accurate Lipschitz bounds for neural networks. Specifically, the LipSDP approach …

Despite recent success, state-of-the-art learning-based models remain highly vulnerable to
input changes such as adversarial examples. In order to obtain certifiable robustness …

Certified defenses against adversarial attacks offer formal guarantees on the robustness of a
model, making them more reliable than empirical methods such as adversarial training …

A key challenge, supported both theoretically and empirically, is that robustness demands
greater network capacity and more data than standard training. However, effectively adding …

The robustness of image segmentation has been an important research topic in the past few
years as segmentation models have reached production-level accuracy. However, like …