Multi-modal and multi-instance fusion for biometric cryptosystems

Abstract

Biometric cryptosystems allow cryptographic privacy protection for biometric reference data without storing a secret key. However, their security is inherently limited by the discriminative information content of the biometric feature data. Given the currently exploitable entropy of biometric features, one of the most promising approaches to achieve high privacy levels is to combine several biometric modalities or several instances of the same biometric modality. In this contribution, we theoretically analyze multibiometric fusion strategies for biometric cryptosystems with respect to their impact on security and recognition accuracy. We also introduce hash level as a new fusion level. Furthermore, we give a more detailed analysis for the most prominent schemes, the Fuzzy Commitment Scheme and the Fuzzy Vault.