Abstract
Fuzzy commitment is an efficient template protection algorithm that can improve security and safeguard privacy of biometrics. Existing theoretical security analysis has proved that although privacy leakage is unavoidable, perfect security from information-theoretical points of view is possible when bits extracted from biometric features are uniformly and independently distributed. Unfortunately, this strict condition is difficult to fulfill in practice. In many applications, dependency of binary features is ignored and security is thus suspected to be highly overestimated. This paper gives a comprehensive analysis on security and privacy of fuzzy commitment regarding empirical evaluation. The criteria representing requirements in practical applications are investigated and measured quantitatively in an existing protection system for 3D face recognition. The evaluation results show that a very significant reduction of security and enlargement of privacy leakage occur due to the dependency of biometric features. This work shows that in practice, one has to explicitly measure the security and privacy instead of trusting results under non-realistic assumptions.
Original language | English |
---|---|
Title of host publication | 2011 International Joint Conference on Biometrics (IJCB 2011) |
Subtitle of host publication | Washington, DC, USA, 11-13 October 2011 |
Place of Publication | Piscataway, NJ |
Publisher | IEEE Computer Society |
Pages | 1-8 |
Number of pages | 8 |
ISBN (Print) | 978-1-4577-1359-0 |
DOIs | |
Publication status | Published - 11 Oct 2011 |
Event | 2011 IEEE International Joint Conference on Biometrics, IJCB 2011 - Doubletree Hotel Crystal City, Washington, United States Duration: 11 Oct 2011 → 13 Oct 2011 |
Conference
Conference | 2011 IEEE International Joint Conference on Biometrics, IJCB 2011 |
---|---|
Abbreviated title | IJCB |
Country/Territory | United States |
City | Washington |
Period | 11/10/11 → 13/10/11 |
Keywords
- SCS-Safety
- EWI-21735
- Template protecion
- fuzzy commitment
- Biometrics
- 3D Face recognition
- IR-80033
- METIS-286310