`

Timezone: »

 
Certifiably Robust Variational Autoencoders
Ben Barrett · Alexander Camuto · Matthew Willetts · Thomas Rainforth

@
in Bayesian Deep Learning »
Event URL: https://openreview.net/forum?id=fa_hua3dtnf »

We derive bounds on the minimal size of an input perturbation required to change a VAE’s reconstruction by more than an allowed amount, with these bounds depending on key parameters such as the Lipschitz constants of the encoder and decoder. Our bounds allow one to specify a desired level of robustness upfront and then train a VAE that is certified to achieve this robustness.

Author Information

Ben Barrett (University of Oxford)
Alexander Camuto (University of Oxford & The Alan Turing Institute)
Matthew Willetts (University College London)
Thomas Rainforth (University of Oxford)

More from the Same Authors