Secure Biometrics

9 December 2010

We’ve released our code and paper on efficient privacy-preserving biometric identification:

Yan Huang (University of Virginia), Lior Malka (Intel/University of Maryland), David Evans (University of Virginia), and Jonathan Katz (University of Maryland). Efficient Privacy-Preserving Biometric Identification. To appear in 18th Network and Distributed System Security Conference (NDSS 2011), 6-9 February 2011. [PDF, 14 pages]

We present an efficient matching protocol that can be used in many privacy-preserving biometric identification systems in the semi-honest setting. Our most general technical contribution is a new backtracking protocol that uses the by-product of evaluating a garbled circuit to enable efficient oblivious information retrieval. We also present a more efficient protocol for computing the Euclidean distances of vectors, and optimized circuits for finding the closest match between a point held by one party and a set of points held by another. We evaluate our protocols by implementing a practical privacy-preserving fingerprint matching system.

Yan will present the paper at NDSS in February. The code for our system is available under the MIT open source license.


flickr cc: didbygraham