Design and analysis of fuzzy extractors for faces

Yagiz Sutcu, Qiming Li, Nasir Memon

Research output: Chapter in Book/Report/Conference proceedingConference contribution

Abstract

It is both crucial and challenging to protect biometric data used for biometric identification and authentication systems, while keeping the systems user friendly. We study the design and analysis of biometric data protection schemes based on fuzzy extractors. There are limitations in previous fuzzy extractors, which make them difficult to handle continuous feature spaces, entropy estimation, and feature selection. We proposed a scheme based on PCA features and a recently proposed fuzzy extractor for continuous domains. We conduct experiments using the ORL face database, and analyze carefully the entropies and the resulting security of the system. We explore and compare different ways to select and combine features, and show that randomization plays an important role in both security, performance and cancelability. Furthermore, proposed feature selection does yield better estimation of the final key strength. Keywords: Biometrics, security, template protection, entropy analysis.

Original languageEnglish (US)
Title of host publicationOptics and Photonics in Global Homeland Security V and Biometric Technology for Human Identification VI
Volume7306
DOIs
StatePublished - 2009
EventOptics and Photonics in Global Homeland Security V and Biometric Technology for Human Identification VI - Orlando, FL, United States
Duration: Apr 13 2009Apr 16 2009

Other

OtherOptics and Photonics in Global Homeland Security V and Biometric Technology for Human Identification VI
CountryUnited States
CityOrlando, FL
Period4/13/094/16/09

Fingerprint

biometrics
Extractor
Biometrics
Face
Entropy
entropy
Feature Selection
Feature extraction
Data privacy
Randomisation
Feature Space
Authentication
Template
templates
Design
Experiment
Experiments

Keywords

  • Biometrics
  • Entropy analysis
  • Security
  • Template protection

ASJC Scopus subject areas

  • Applied Mathematics
  • Computer Science Applications
  • Electrical and Electronic Engineering
  • Electronic, Optical and Magnetic Materials
  • Condensed Matter Physics

Cite this

Sutcu, Y., Li, Q., & Memon, N. (2009). Design and analysis of fuzzy extractors for faces. In Optics and Photonics in Global Homeland Security V and Biometric Technology for Human Identification VI (Vol. 7306). [73061X] https://doi.org/10.1117/12.820571

Design and analysis of fuzzy extractors for faces. / Sutcu, Yagiz; Li, Qiming; Memon, Nasir.

Optics and Photonics in Global Homeland Security V and Biometric Technology for Human Identification VI. Vol. 7306 2009. 73061X.

Research output: Chapter in Book/Report/Conference proceedingConference contribution

Sutcu, Y, Li, Q & Memon, N 2009, Design and analysis of fuzzy extractors for faces. in Optics and Photonics in Global Homeland Security V and Biometric Technology for Human Identification VI. vol. 7306, 73061X, Optics and Photonics in Global Homeland Security V and Biometric Technology for Human Identification VI, Orlando, FL, United States, 4/13/09. https://doi.org/10.1117/12.820571
Sutcu Y, Li Q, Memon N. Design and analysis of fuzzy extractors for faces. In Optics and Photonics in Global Homeland Security V and Biometric Technology for Human Identification VI. Vol. 7306. 2009. 73061X https://doi.org/10.1117/12.820571
Sutcu, Yagiz ; Li, Qiming ; Memon, Nasir. / Design and analysis of fuzzy extractors for faces. Optics and Photonics in Global Homeland Security V and Biometric Technology for Human Identification VI. Vol. 7306 2009.
@inproceedings{169200cde7484e92898dafb406924e69,
title = "Design and analysis of fuzzy extractors for faces",
abstract = "It is both crucial and challenging to protect biometric data used for biometric identification and authentication systems, while keeping the systems user friendly. We study the design and analysis of biometric data protection schemes based on fuzzy extractors. There are limitations in previous fuzzy extractors, which make them difficult to handle continuous feature spaces, entropy estimation, and feature selection. We proposed a scheme based on PCA features and a recently proposed fuzzy extractor for continuous domains. We conduct experiments using the ORL face database, and analyze carefully the entropies and the resulting security of the system. We explore and compare different ways to select and combine features, and show that randomization plays an important role in both security, performance and cancelability. Furthermore, proposed feature selection does yield better estimation of the final key strength. Keywords: Biometrics, security, template protection, entropy analysis.",
keywords = "Biometrics, Entropy analysis, Security, Template protection",
author = "Yagiz Sutcu and Qiming Li and Nasir Memon",
year = "2009",
doi = "10.1117/12.820571",
language = "English (US)",
isbn = "9780819475725",
volume = "7306",
booktitle = "Optics and Photonics in Global Homeland Security V and Biometric Technology for Human Identification VI",

}

TY - GEN

T1 - Design and analysis of fuzzy extractors for faces

AU - Sutcu, Yagiz

AU - Li, Qiming

AU - Memon, Nasir

PY - 2009

Y1 - 2009

N2 - It is both crucial and challenging to protect biometric data used for biometric identification and authentication systems, while keeping the systems user friendly. We study the design and analysis of biometric data protection schemes based on fuzzy extractors. There are limitations in previous fuzzy extractors, which make them difficult to handle continuous feature spaces, entropy estimation, and feature selection. We proposed a scheme based on PCA features and a recently proposed fuzzy extractor for continuous domains. We conduct experiments using the ORL face database, and analyze carefully the entropies and the resulting security of the system. We explore and compare different ways to select and combine features, and show that randomization plays an important role in both security, performance and cancelability. Furthermore, proposed feature selection does yield better estimation of the final key strength. Keywords: Biometrics, security, template protection, entropy analysis.

AB - It is both crucial and challenging to protect biometric data used for biometric identification and authentication systems, while keeping the systems user friendly. We study the design and analysis of biometric data protection schemes based on fuzzy extractors. There are limitations in previous fuzzy extractors, which make them difficult to handle continuous feature spaces, entropy estimation, and feature selection. We proposed a scheme based on PCA features and a recently proposed fuzzy extractor for continuous domains. We conduct experiments using the ORL face database, and analyze carefully the entropies and the resulting security of the system. We explore and compare different ways to select and combine features, and show that randomization plays an important role in both security, performance and cancelability. Furthermore, proposed feature selection does yield better estimation of the final key strength. Keywords: Biometrics, security, template protection, entropy analysis.

KW - Biometrics

KW - Entropy analysis

KW - Security

KW - Template protection

UR - http://www.scopus.com/inward/record.url?scp=69949122147&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=69949122147&partnerID=8YFLogxK

U2 - 10.1117/12.820571

DO - 10.1117/12.820571

M3 - Conference contribution

SN - 9780819475725

VL - 7306

BT - Optics and Photonics in Global Homeland Security V and Biometric Technology for Human Identification VI

ER -