Correlation-resistant fuzzy vault for fingerprints

Abstract

The fuzzy vault is one of the most popular biometric encryption schemes for protecting fingerprint data. However, its implementation faces two challenges: First, the fingerprints need to be aligned. Some publications have proposed the storage of auxiliary data to assist alignment, but these data may leak information about the biometric features. Secondly, the fuzzy vault is susceptible to attacks that correlate the data from two protected templates, which does not only violate the requirement of unlinkability but also allows the recovery of the biometric data. In this work, we present a fuzzy vault construction for fingerprint data (minutiae) that addresses both issues. We do so by applying an absolute alignment method to the fingerprints, performing a quantization of the minutiae positions to a grid, and using all grid points unoccupied by minutiae as chaff. This approach results in all vaults containing the same set of points. In order to improve recognition performance, we also use the minutiae's angles and types. We present experimental evaluations and compare the results with the existing works on fuzzy fingerprint vault.