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...

תיאור מלא

מידע ביבליוגרפי
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