AriaNN: Low-Interaction Privacy-Preserving Deep Learning via Function Secret Sharing

We propose AriaNN, a low-interaction privacy-preserving framework for private neural network training and inference on sensitive data.

Guardado en:

Detalles Bibliográficos
Autores principales:	Ryffel Théo, Tholoniat Pierre, Pointcheval David, Bach Francis
Formato:	article
Lenguaje:	EN
Publicado:	Sciendo 2022
Materias:	multi party computation function secret sharing secure comparison deep learning Ethics BJ1-1725 Electronic computers. Computer science QA75.5-76.95
Acceso en línea:	https://doaj.org/article/5d826b5e3d9b49df9f7ebc14cb47bd78
Etiquetas:	Agregar Etiqueta Sin Etiquetas, Sea el primero en etiquetar este registro!

id	oai:doaj.org-article:5d826b5e3d9b49df9f7ebc14cb47bd78
record_format	dspace
spelling	oai:doaj.org-article:5d826b5e3d9b49df9f7ebc14cb47bd782021-12-05T14:11:10ZAriaNN: Low-Interaction Privacy-Preserving Deep Learning via Function Secret Sharing2299-098410.2478/popets-2022-0015https://doaj.org/article/5d826b5e3d9b49df9f7ebc14cb47bd782022-01-01T00:00:00Zhttps://doi.org/10.2478/popets-2022-0015https://doaj.org/toc/2299-0984We propose AriaNN, a low-interaction privacy-preserving framework for private neural network training and inference on sensitive data.Ryffel ThéoTholoniat PierrePointcheval DavidBach FrancisSciendoarticlemulti party computationfunction secret sharingsecure comparisondeep learningEthicsBJ1-1725Electronic computers. Computer scienceQA75.5-76.95ENProceedings on Privacy Enhancing Technologies, Vol 2022, Iss 1, Pp 291-316 (2022)
institution	DOAJ
collection	DOAJ
language	EN
topic	multi party computation function secret sharing secure comparison deep learning Ethics BJ1-1725 Electronic computers. Computer science QA75.5-76.95
spellingShingle	multi party computation function secret sharing secure comparison deep learning Ethics BJ1-1725 Electronic computers. Computer science QA75.5-76.95 Ryffel Théo Tholoniat Pierre Pointcheval David Bach Francis AriaNN: Low-Interaction Privacy-Preserving Deep Learning via Function Secret Sharing
description	We propose AriaNN, a low-interaction privacy-preserving framework for private neural network training and inference on sensitive data.
format	article
author	Ryffel Théo Tholoniat Pierre Pointcheval David Bach Francis
author_facet	Ryffel Théo Tholoniat Pierre Pointcheval David Bach Francis
author_sort	Ryffel Théo
title	AriaNN: Low-Interaction Privacy-Preserving Deep Learning via Function Secret Sharing
title_short	AriaNN: Low-Interaction Privacy-Preserving Deep Learning via Function Secret Sharing
title_full	AriaNN: Low-Interaction Privacy-Preserving Deep Learning via Function Secret Sharing
title_fullStr	AriaNN: Low-Interaction Privacy-Preserving Deep Learning via Function Secret Sharing
title_full_unstemmed	AriaNN: Low-Interaction Privacy-Preserving Deep Learning via Function Secret Sharing
title_sort	ariann: low-interaction privacy-preserving deep learning via function secret sharing
publisher	Sciendo
publishDate	2022
url	https://doaj.org/article/5d826b5e3d9b49df9f7ebc14cb47bd78
work_keys_str_mv	AT ryffeltheo ariannlowinteractionprivacypreservingdeeplearningviafunctionsecretsharing AT tholoniatpierre ariannlowinteractionprivacypreservingdeeplearningviafunctionsecretsharing AT pointchevaldavid ariannlowinteractionprivacypreservingdeeplearningviafunctionsecretsharing AT bachfrancis ariannlowinteractionprivacypreservingdeeplearningviafunctionsecretsharing
_version_	1718371301161172992

AriaNN: Low-Interaction Privacy-Preserving Deep Learning via Function Secret Sharing

Ejemplares similares