Adversarial robustness guarantees for classification with Gaussian Processes
We investigate adversarial robustness of Gaussian Process classification (GPC) models. Specifically, given a compact subset of the input space T⊆ℝd enclosing a test point x∗ and a GPC trained on a dataset , we aim to compute the minimum and the maximum classification probability for the GPC over al...
Autori principali: | Blaas, A, Patane, A, Laurenti, L, Cardelli, L, Kwiatkowska, M, Roberts, S |
---|---|
Natura: | Conference item |
Lingua: | English |
Pubblicazione: |
Proceedings of Machine Learning Research
2020
|
Documenti analoghi
-
Adversarial robustness guarantees for Gaussian processes
di: Patane, A, et al.
Pubblicazione: (2022) -
Robustness guarantees for Bayesian inference with Gaussian processes
di: Cardelli, L, et al.
Pubblicazione: (2019) -
Safety guarantees for iterative predictions with Gaussian Processes
di: Polymenakos, K, et al.
Pubblicazione: (2021) -
Statistical guarantees for the robustness of Bayesian neural networks
di: Cardelli, L, et al.
Pubblicazione: (2019) -
On the adversarial robustness of Gaussian processes
di: Patanè, A
Pubblicazione: (2020)