Privacy-aware Biometrics: Design and Implementation of a Multimodal Verification System

PDF
0.3MB

Stelvio Cimato
Università di Milano
Italy

Marco Gamassi
Università di Milano
Italy

Vincenzo Piuri
Università di Milano
Italy

Roberto Sassi
Università di Milano
Italy

Fabio Scotti
Università di Milano
Italy

Abstract:
A serious concern in the design and use of biometric authentication systems is the privacy protection of the information derived from human biometric traits, since the latter cannot be replaced when the former is lost or stolen. Unfortunately, the usage of conventional cryptographic strategies to protect such an information is intrinsically fragile from the privacy point of view: if the encryption keys are unveiled the biometric information will not be protected anymore. Recently, many approaches have been proposed combining cryptography and biometrics to move a step further and build the protection in the biometric templates themselves. While these solutions can increase the confidence in biometric systems when biometric information is stored for verification, they have been shown difficult to apply to real biometrics.

In this work we present a privacy-aware biometric authentication technique that exploits multiple biometric traits. It ensures privacy protection and allows the extraction of secure identifiers by means of cryptographic primitives. Also, the design methodology adopts a modular strategy: this allows for tuning the biometric encryption structure to the privacy degree requested by the application, thus enabling the support of different levels of protection. We also discuss the implementation of our approach by considering, as a significant example, the combination of iris and fingerprint biometrics. The resulting experimental data are also presented.