Differential privacy for eye tracking with temporal correlations.

New generation head-mounted displays, such as VR and AR glasses, are coming into the market with already integrated eye tracking and are expected to enable novel ways of human-computer interaction in numerous applications. However, since eye movement properties contain biometric information, privacy...

Descripción completa

Guardado en:

Detalles Bibliográficos
Autores principales:	Efe Bozkir, Onur Günlü, Wolfgang Fuhl, Rafael F Schaefer, Enkelejda Kasneci
Formato:	article
Lenguaje:	EN
Publicado:	Public Library of Science (PLoS) 2021
Materias:	Medicine R Science Q
Acceso en línea:	https://doaj.org/article/0ae3190570e841dba3fe0f494248baef
Etiquetas:	Agregar Etiqueta Sin Etiquetas, Sea el primero en etiquetar este registro!

id	oai:doaj.org-article:0ae3190570e841dba3fe0f494248baef
record_format	dspace
spelling	oai:doaj.org-article:0ae3190570e841dba3fe0f494248baef2021-12-02T20:17:54ZDifferential privacy for eye tracking with temporal correlations.1932-620310.1371/journal.pone.0255979https://doaj.org/article/0ae3190570e841dba3fe0f494248baef2021-01-01T00:00:00Zhttps://doi.org/10.1371/journal.pone.0255979https://doaj.org/toc/1932-6203New generation head-mounted displays, such as VR and AR glasses, are coming into the market with already integrated eye tracking and are expected to enable novel ways of human-computer interaction in numerous applications. However, since eye movement properties contain biometric information, privacy concerns have to be handled properly. Privacy-preservation techniques such as differential privacy mechanisms have recently been applied to eye movement data obtained from such displays. Standard differential privacy mechanisms; however, are vulnerable due to temporal correlations between the eye movement observations. In this work, we propose a novel transform-coding based differential privacy mechanism to further adapt it to the statistics of eye movement feature data and compare various low-complexity methods. We extend the Fourier perturbation algorithm, which is a differential privacy mechanism, and correct a scaling mistake in its proof. Furthermore, we illustrate significant reductions in sample correlations in addition to query sensitivities, which provide the best utility-privacy trade-off in the eye tracking literature. Our results provide significantly high privacy without any essential loss in classification accuracies while hiding personal identifiers.Efe BozkirOnur GünlüWolfgang FuhlRafael F SchaeferEnkelejda KasneciPublic Library of Science (PLoS)articleMedicineRScienceQENPLoS ONE, Vol 16, Iss 8, p e0255979 (2021)
institution	DOAJ
collection	DOAJ
language	EN
topic	Medicine R Science Q
spellingShingle	Medicine R Science Q Efe Bozkir Onur Günlü Wolfgang Fuhl Rafael F Schaefer Enkelejda Kasneci Differential privacy for eye tracking with temporal correlations.
description	New generation head-mounted displays, such as VR and AR glasses, are coming into the market with already integrated eye tracking and are expected to enable novel ways of human-computer interaction in numerous applications. However, since eye movement properties contain biometric information, privacy concerns have to be handled properly. Privacy-preservation techniques such as differential privacy mechanisms have recently been applied to eye movement data obtained from such displays. Standard differential privacy mechanisms; however, are vulnerable due to temporal correlations between the eye movement observations. In this work, we propose a novel transform-coding based differential privacy mechanism to further adapt it to the statistics of eye movement feature data and compare various low-complexity methods. We extend the Fourier perturbation algorithm, which is a differential privacy mechanism, and correct a scaling mistake in its proof. Furthermore, we illustrate significant reductions in sample correlations in addition to query sensitivities, which provide the best utility-privacy trade-off in the eye tracking literature. Our results provide significantly high privacy without any essential loss in classification accuracies while hiding personal identifiers.
format	article
author	Efe Bozkir Onur Günlü Wolfgang Fuhl Rafael F Schaefer Enkelejda Kasneci
author_facet	Efe Bozkir Onur Günlü Wolfgang Fuhl Rafael F Schaefer Enkelejda Kasneci
author_sort	Efe Bozkir
title	Differential privacy for eye tracking with temporal correlations.
title_short	Differential privacy for eye tracking with temporal correlations.
title_full	Differential privacy for eye tracking with temporal correlations.
title_fullStr	Differential privacy for eye tracking with temporal correlations.
title_full_unstemmed	Differential privacy for eye tracking with temporal correlations.
title_sort	differential privacy for eye tracking with temporal correlations.
publisher	Public Library of Science (PLoS)
publishDate	2021
url	https://doaj.org/article/0ae3190570e841dba3fe0f494248baef
work_keys_str_mv	AT efebozkir differentialprivacyforeyetrackingwithtemporalcorrelations AT onurgunlu differentialprivacyforeyetrackingwithtemporalcorrelations AT wolfgangfuhl differentialprivacyforeyetrackingwithtemporalcorrelations AT rafaelfschaefer differentialprivacyforeyetrackingwithtemporalcorrelations AT enkelejdakasneci differentialprivacyforeyetrackingwithtemporalcorrelations
_version_	1718374327584292864

Differential privacy for eye tracking with temporal correlations.

Ejemplares similares