Exploring presentation attack vulnerability and usability of face recognition systems

Abstract Commercial face recognition software intended for the use of access control is evaluated. Most of the systems are to be used with hand‐held devices (smartphones). The systems under test also contain three stationary systems designed to unlock doors or other secure entrance systems. While sp...

Full description

Saved in:
Bibliographic Details
Main Authors: Heinz Hofbauer, Luca Debiasi, Susanne Kränkl, Andreas Uhl
Format: Article
Language:English
Published: Wiley 2021-03-01
Series:IET Biometrics
Subjects:
Online Access:https://doi.org/10.1049/bme2.12015
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1849686502866419712
author Heinz Hofbauer
Luca Debiasi
Susanne Kränkl
Andreas Uhl
author_facet Heinz Hofbauer
Luca Debiasi
Susanne Kränkl
Andreas Uhl
author_sort Heinz Hofbauer
collection DOAJ
description Abstract Commercial face recognition software intended for the use of access control is evaluated. Most of the systems are to be used with hand‐held devices (smartphones). The systems under test also contain three stationary systems designed to unlock doors or other secure entrance systems. While specifics of the systems cannot be gone in‐depth under test (due to NDAs), the results of the evaluation of liveness detection (or presentation attack detection) with different complexity levels and template comparison performance are presented. The robustness against presentation attack is compares with the systems usability, and highlight where current commercial of the shelf systems (COTS) stand in that regard. The results focusing on the tradeoff between acceptance, linked with usability, and security are examined, which usually negatively impacts usability. A first extension of the attacks to systems using the NIR spectrum for imaging is also presented. This is mostly limited to stationary systems as they can include dedicated hardware with NIR capabilities. This is their main differentiation to most COTS systems running on smartphones, which do not rely on dedicated hardware. Though exceptions to this already exist for example in Apple devices. It is shown that most of the systems are not secure and not user friendly, having huge problems with difficult lighting conditions while only providing the most basic liveness or presentation attack detection capabilities.
format Article
id doaj-art-c003ecc5a218445ab2dfd0bf7b70f2d0
institution DOAJ
issn 2047-4938
2047-4946
language English
publishDate 2021-03-01
publisher Wiley
record_format Article
series IET Biometrics
spelling doaj-art-c003ecc5a218445ab2dfd0bf7b70f2d02025-08-20T03:22:41ZengWileyIET Biometrics2047-49382047-49462021-03-0110221923210.1049/bme2.12015Exploring presentation attack vulnerability and usability of face recognition systemsHeinz Hofbauer0Luca Debiasi1Susanne Kränkl2Andreas Uhl3Multimedia Signal Processing and Security Lab Paris Lodron University of Salzburg Salzburg AustriaMultimedia Signal Processing and Security Lab Paris Lodron University of Salzburg Salzburg AustriaVeridos LLC. Munich GermanyMultimedia Signal Processing and Security Lab Paris Lodron University of Salzburg Salzburg AustriaAbstract Commercial face recognition software intended for the use of access control is evaluated. Most of the systems are to be used with hand‐held devices (smartphones). The systems under test also contain three stationary systems designed to unlock doors or other secure entrance systems. While specifics of the systems cannot be gone in‐depth under test (due to NDAs), the results of the evaluation of liveness detection (or presentation attack detection) with different complexity levels and template comparison performance are presented. The robustness against presentation attack is compares with the systems usability, and highlight where current commercial of the shelf systems (COTS) stand in that regard. The results focusing on the tradeoff between acceptance, linked with usability, and security are examined, which usually negatively impacts usability. A first extension of the attacks to systems using the NIR spectrum for imaging is also presented. This is mostly limited to stationary systems as they can include dedicated hardware with NIR capabilities. This is their main differentiation to most COTS systems running on smartphones, which do not rely on dedicated hardware. Though exceptions to this already exist for example in Apple devices. It is shown that most of the systems are not secure and not user friendly, having huge problems with difficult lighting conditions while only providing the most basic liveness or presentation attack detection capabilities.https://doi.org/10.1049/bme2.12015authorisationface recognitionsmart phones
spellingShingle Heinz Hofbauer
Luca Debiasi
Susanne Kränkl
Andreas Uhl
Exploring presentation attack vulnerability and usability of face recognition systems
IET Biometrics
authorisation
face recognition
smart phones
title Exploring presentation attack vulnerability and usability of face recognition systems
title_full Exploring presentation attack vulnerability and usability of face recognition systems
title_fullStr Exploring presentation attack vulnerability and usability of face recognition systems
title_full_unstemmed Exploring presentation attack vulnerability and usability of face recognition systems
title_short Exploring presentation attack vulnerability and usability of face recognition systems
title_sort exploring presentation attack vulnerability and usability of face recognition systems
topic authorisation
face recognition
smart phones
url https://doi.org/10.1049/bme2.12015
work_keys_str_mv AT heinzhofbauer exploringpresentationattackvulnerabilityandusabilityoffacerecognitionsystems
AT lucadebiasi exploringpresentationattackvulnerabilityandusabilityoffacerecognitionsystems
AT susannekrankl exploringpresentationattackvulnerabilityandusabilityoffacerecognitionsystems
AT andreasuhl exploringpresentationattackvulnerabilityandusabilityoffacerecognitionsystems