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...
Những tác giả chính: | Wicker, M, Laurenti, L, Patane, A, Chen, Z, Zhang, Z, Kwiatkowska, M |
---|---|
Định dạng: | Conference item |
Ngôn ngữ: | English |
Được phát hành: |
Journal of Machine Learning Research
2021
|
Những quyển sách tương tự
-
Adversarial robustness certification for Bayesian neural networks
Bằng: Wicker, M, et al.
Được phát hành: (2024) -
Robustness guarantees for Bayesian inference with Gaussian processes
Bằng: Cardelli, L, et al.
Được phát hành: (2019) -
Statistical guarantees for the robustness of Bayesian neural networks
Bằng: Cardelli, L, et al.
Được phát hành: (2019) -
Adversarial robustness guarantees for Gaussian processes
Bằng: Patane, A, et al.
Được phát hành: (2022) -
Probabilistic safety for bayesian neural networks
Bằng: Wicker, M, et al.
Được phát hành: (2020)