Neural network verification aims to provide provable bounds for the outp...
We study a new family of inverse problems for recovering representations...
We present a scalable technique for upper bounding the Lipschitz constan...
In the context of the recent COVID-19 outbreak, quarantine has been used...
The Lipschitz constant of a neural network is a useful metric for provab...
We propose a novel method for computing exact pointwise robustness of de...
Recent work has shown that additive threat models, which only permit the...