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...
المؤلفون الرئيسيون: | Wicker, M, Laurenti, L, Patane, A, Chen, Z, Zhang, Z, Kwiatkowska, M |
---|---|
التنسيق: | Conference item |
اللغة: | English |
منشور في: |
Journal of Machine Learning Research
2021
|
مواد مشابهة
-
Adversarial robustness certification for Bayesian neural networks
حسب: Wicker, M, وآخرون
منشور في: (2024) -
Robustness guarantees for Bayesian inference with Gaussian processes
حسب: Cardelli, L, وآخرون
منشور في: (2019) -
Statistical guarantees for the robustness of Bayesian neural networks
حسب: Cardelli, L, وآخرون
منشور في: (2019) -
Adversarial robustness guarantees for Gaussian processes
حسب: Patane, A, وآخرون
منشور في: (2022) -
Probabilistic safety for bayesian neural networks
حسب: Wicker, M, وآخرون
منشور في: (2020)