Probabilistic safety for bayesian neural networks

We study probabilistic safety for Bayesian Neural Networks (BNNs) under adversarial input perturbations. Given a compact set of input points, T ⊆ R m, we study the probability w.r.t. the BNN posterior that all the points in T are mapped to the same region S in the output space. In particular, this c...

Full description

Bibliographic Details
Main Authors: Wicker, M, Laurenti, L, Patane, A, Kwiatkowska, M
Format: Conference item
Language:English
Published: Journal of Machine Learning Research 2020