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:
-
-
(Version of record, pdf, 1.0MB)
-
- Publication website:
- https://proceedings.mlr.press/v130/camuto21a.html
Authors
Bibliographic Details
- 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
Item Description
- Language:
- English
- Keywords:
- Pubs id:
-
1170795
- Local pid:
- pubs:1170795
- Deposit date:
- 2023-01-20
Terms of use
- Copyright holder:
- Camuto et al.
- Copyright date:
- 2021
- Rights statement:
- Copyright 2021 by the author(s).
Metrics
If you are the owner of this record, you can report an update to it here: Report update to this record