Bayesian inference with certifiable adversarial robustness
We consider adversarial training of deep neural networks through the lens of Bayesian learning and present a principled framework for adversarial training of Bayesian Neural Networks (BNNs) with certifiable guarantees. We rely on techniques from constraint relaxation of non-convex optimisation probl...
Main Authors: | Wicker, M, Laurenti, L, Patane, A, Chen, Z, Zhang, Z, Kwiatkowska, M |
---|---|
פורמט: | Conference item |
שפה: | English |
יצא לאור: |
Journal of Machine Learning Research
2021
|
פריטים דומים
-
Adversarial robustness certification for Bayesian neural networks
מאת: Wicker, M, et al.
יצא לאור: (2024) -
Robustness guarantees for Bayesian inference with Gaussian processes
מאת: Cardelli, L, et al.
יצא לאור: (2019) -
Statistical guarantees for the robustness of Bayesian neural networks
מאת: Cardelli, L, et al.
יצא לאור: (2019) -
Adversarial robustness guarantees for Gaussian processes
מאת: Patane, A, et al.
יצא לאור: (2022) -
Probabilistic safety for bayesian neural networks
מאת: Wicker, M, et al.
יצא לאור: (2020)