Adversarial robustness guarantees for classification with gaussian processes

A Blaas, A Patane, L Laurenti… - International …, 2020 - proceedings.mlr.press
We investigate adversarial robustness of Gaussian Process classification (GPC) models.
Specifically, given a compact subset of the input space $ T\subseteq\mathbb {R}^ d …

Adversarial robustness guarantees for gaussian processes

A Patane, A Blaas, L Laurenti, L Cardelli… - Journal of Machine …, 2022 - jmlr.org
Gaussian processes (GPs) enable principled computation of model uncertainty, making
them attractive for safety-critical applications. Such scenarios demand that GP decisions are …

[引用][C] Robustness quantification for classification with gaussian processes

A Blaas, L Laurenti, A Patane, L Cardelli… - arXiv preprint arXiv …, 2019