Privacy Preserving Technique for Set-Based Biometric Authentication Using Reed-Solomon Decoding

In this work, we present a single-factor biometric authentication system that provides template security against an adversarial server while allowing error-tolerant matching. Our approach is to secure templates represented as sets using error-correcting codes and Reed-Solomon decoding. To accomplish this, each element in the set is combined with a random codeword and a secret share is computed using the codeword and a Reed-Solomon based secret sharing scheme. These random codewords provide uncertainty for an attacker, while the genuine user can decode to the correct values for verification. Without a reading from the enrolling biometric the shares will appear random, thus protecting the users biometric. We show implementation results for this system on fingerprints using pairs of minutia points. Our system overcomes many common weaknesses for template security systems including replay attacks, malicious servers, eavesdroppers, and record multiplicity attacks.