Conference item icon

Conference item

Towards a theoretical understanding of the robustness of variational autoencoders

Abstract:

We make inroads into understanding the robustness of Variational Autoencoders (VAEs) to adversarial attacks and other input perturbations. While previous work has developed algorithmic approaches to attacking and defending VAEs, there remains a lack of formalization for what it means for a VAE to be robust. To address this, we develop a novel criterion for robustness in probabilistic models: r -robustness. We then use this to construct the first theoretical results for the robustness of VAEs,...

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

Actions


Access Document


Files:
Publication website:
https://proceedings.mlr.press/v130/camuto21a.html

Authors


More by this author
Institution:
University of Oxford
Division:
MPLS
Department:
Engineering Science
Role:
Author
ORCID:
0000-0002-9305-9268
More by this author
Institution:
University of Oxford
Division:
MPLS
Department:
Statistics
Oxford college:
Christ Church
Role:
Author
Publisher:
Journal of Machine Learning Research Publisher's website
Series:
Proceedings of Machine Learning Research
Series number:
130
Pages:
3565-3573
Publication date:
2021-03-18
Acceptance date:
2021-01-14
Event title:
24th International Conference on Artificial Intelligence and Statistics (AISTATS 2021)
Event location:
San Diego, California, USA
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:
1170795
Local pid:
pubs:1170795
Deposit date:
2023-01-20

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