2021-03-18-camuto21a.md

title	abstract	layout	series	publisher	issn	id	month	tex_title	firstpage	lastpage	page	order	cycles	bibtex_author	author	date	address	container-title	volume	genre	issued	pdf	extras
Towards a Theoretical Understanding of the Robustness of Variational Autoencoders	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, deriving margins in the input space for which we can provide guarantees about the resulting reconstruction. Informally, we are able to define a region within which any perturbation will produce a reconstruction that is similar to the original reconstruction. To support our analysis, we show that VAEs trained using disentangling methods not only score well under our robustness metrics, but that the reasons for this can be interpreted through our theoretical results.	inproceedings	Proceedings of Machine Learning Research	PMLR	2640-3498	camuto21a	0	Towards a Theoretical Understanding of the Robustness of Variational Autoencoders	3565	3573	3565-3573	3565	false	Camuto, Alexander and Willetts, Matthew and Roberts, Stephen and Holmes, Chris and Rainforth, Tom	given family Alexander Camuto given family Matthew Willetts given family Stephen Roberts given family Chris Holmes given family Tom Rainforth	2021-03-18		Proceedings of The 24th International Conference on Artificial Intelligence and Statistics	130	inproceedings	date-parts 2021 3 18	http://proceedings.mlr.press/v130/camuto21a/camuto21a.pdf	label link Supplementary ZIP http://proceedings.mlr.press/v130/camuto21a/camuto21a-supp.zip