Conference item icon

Conference item

Bayesian inference with certifiable adversarial robustness

Abstract:

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 problems and modify the standard cross-entropy error model to enforce posterior robustness to worst-case perturbations in ϵ−balls around input points. We illustrate how the resulting framework can be co...

Expand abstract
Publication status:
Published
Peer review status:
Peer reviewed

Actions


Access Document


Files:
Publication website:
http://proceedings.mlr.press/v130/wicker21a.html

Authors


More by this author
Institution:
University of Oxford
Division:
MPLS
Department:
Computer Science
Role:
Author
More by this author
Institution:
University of Oxford
Division:
MPLS
Department:
Computer Science
Role:
Author
More by this author
Institution:
University of Oxford
Division:
MPLS
Department:
Computer Science
Role:
Author
Publisher:
Journal of Machine Learning Research Publisher's website
Series:
Proceedings of Machine Learning Research
Series number:
130
Pages:
2431-2439
Publication date:
2021-03-18
Acceptance date:
2021-02-22
Event title:
24th International Conference on Artificial Intelligence and Statistics (AISTATS 2021)
Event location:
Virtual event
Event website:
https://aistats.org/aistats2021/
Event start date:
2021-04-13
Event end date:
2021-04-15
ISSN:
2640-3498
Language:
English
Keywords:
Pubs id:
1164130
Local pid:
pubs:1164130
Deposit date:
2021-03-01

Terms of use


Views and Downloads






If you are the owner of this record, you can report an update to it here: Report update to this record

TO TOP