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...
मुख्य लेखकों: | Blaas, A, Patane, A, Laurenti, L, Cardelli, L, Kwiatkowska, M, Roberts, S |
---|---|
स्वरूप: | Conference item |
भाषा: | English |
प्रकाशित: |
Proceedings of Machine Learning Research
2020
|
समान संसाधन
समान संसाधन
-
Adversarial robustness guarantees for Gaussian processes
द्वारा: Patane, A, और अन्य
प्रकाशित: (2022) -
Robustness guarantees for Bayesian inference with Gaussian processes
द्वारा: Cardelli, L, और अन्य
प्रकाशित: (2019) -
Safety guarantees for iterative predictions with Gaussian Processes
द्वारा: Polymenakos, K, और अन्य
प्रकाशित: (2021) -
Statistical guarantees for the robustness of Bayesian neural networks
द्वारा: Cardelli, L, और अन्य
प्रकाशित: (2019) -
On the adversarial robustness of Gaussian processes
द्वारा: Patanè, A
प्रकाशित: (2020)