Negative Databases for Biometric Data

TL;DR

This paper introduces a novel method for creating biometric negative databases, addressing privacy concerns by enabling secure data representation despite biometric variability.

Contribution

It presents the first known approach to construct and utilize biometric negative databases, overcoming the challenge of biometric data variability.

Findings

Proposed a new biometric negative database construction method

Demonstrated the feasibility of biometric data protection

Addressed the variability issue in biometric comparisons

Abstract

Negative databases - negative representations of a set of data - have been introduced in 2004 to protect the data they contain. Today, no solution is known to constitute biometric negative databases. This is surprising as biometric applications are very demanding of such protection for privacy reasons. The main difficulty comes from the fact that biometric captures of the same trait give different results and comparisons of the stored reference with the fresh captured biometric data has to take into account this variability. In this paper, we give a first answer to this problem by exhibiting a way to create and exploit biometric negative databases.