Privacy-Preserving High-dimensional Data Collection with Federated Generative Autoencoder

Business intelligence and AI services often involve the collection of copious amounts of multidimensional personal data. Since these data usually contain sensitive information of individuals, the direct collection can lead to privacy violations. Local differential privacy (LDP) is currently consider...

Descripción completa

Guardado en:
Detalles Bibliográficos
Autores principales: Jiang Xue, Zhou Xuebing, Grossklags Jens
Formato: article
Lenguaje:EN
Publicado: Sciendo 2022
Materias:
Acceso en línea:https://doaj.org/article/4d7e219b1a474b8e87438097c4846f50
Etiquetas: Agregar Etiqueta
Sin Etiquetas, Sea el primero en etiquetar este registro!
id oai:doaj.org-article:4d7e219b1a474b8e87438097c4846f50
record_format dspace
spelling oai:doaj.org-article:4d7e219b1a474b8e87438097c4846f502021-12-05T14:11:10ZPrivacy-Preserving High-dimensional Data Collection with Federated Generative Autoencoder2299-098410.2478/popets-2022-0024https://doaj.org/article/4d7e219b1a474b8e87438097c4846f502022-01-01T00:00:00Zhttps://doi.org/10.2478/popets-2022-0024https://doaj.org/toc/2299-0984Business intelligence and AI services often involve the collection of copious amounts of multidimensional personal data. Since these data usually contain sensitive information of individuals, the direct collection can lead to privacy violations. Local differential privacy (LDP) is currently considered a state-ofthe-art solution for privacy-preserving data collection. However, existing LDP algorithms are not applicable to high-dimensional data; not only because of the increase in computation and communication cost, but also poor data utility.Jiang XueZhou XuebingGrossklags JensSciendoarticlehigh-dimensional data collectionlocal differential privacyfederated learninggenerative modelsEthicsBJ1-1725Electronic computers. Computer scienceQA75.5-76.95ENProceedings on Privacy Enhancing Technologies, Vol 2022, Iss 1, Pp 481-500 (2022)
institution DOAJ
collection DOAJ
language EN
topic high-dimensional data collection
local differential privacy
federated learning
generative models
Ethics
BJ1-1725
Electronic computers. Computer science
QA75.5-76.95
spellingShingle high-dimensional data collection
local differential privacy
federated learning
generative models
Ethics
BJ1-1725
Electronic computers. Computer science
QA75.5-76.95
Jiang Xue
Zhou Xuebing
Grossklags Jens
Privacy-Preserving High-dimensional Data Collection with Federated Generative Autoencoder
description Business intelligence and AI services often involve the collection of copious amounts of multidimensional personal data. Since these data usually contain sensitive information of individuals, the direct collection can lead to privacy violations. Local differential privacy (LDP) is currently considered a state-ofthe-art solution for privacy-preserving data collection. However, existing LDP algorithms are not applicable to high-dimensional data; not only because of the increase in computation and communication cost, but also poor data utility.
format article
author Jiang Xue
Zhou Xuebing
Grossklags Jens
author_facet Jiang Xue
Zhou Xuebing
Grossklags Jens
author_sort Jiang Xue
title Privacy-Preserving High-dimensional Data Collection with Federated Generative Autoencoder
title_short Privacy-Preserving High-dimensional Data Collection with Federated Generative Autoencoder
title_full Privacy-Preserving High-dimensional Data Collection with Federated Generative Autoencoder
title_fullStr Privacy-Preserving High-dimensional Data Collection with Federated Generative Autoencoder
title_full_unstemmed Privacy-Preserving High-dimensional Data Collection with Federated Generative Autoencoder
title_sort privacy-preserving high-dimensional data collection with federated generative autoencoder
publisher Sciendo
publishDate 2022
url https://doaj.org/article/4d7e219b1a474b8e87438097c4846f50
work_keys_str_mv AT jiangxue privacypreservinghighdimensionaldatacollectionwithfederatedgenerativeautoencoder
AT zhouxuebing privacypreservinghighdimensionaldatacollectionwithfederatedgenerativeautoencoder
AT grossklagsjens privacypreservinghighdimensionaldatacollectionwithfederatedgenerativeautoencoder
_version_ 1718371296993083392