Game-Set-MATCH: Using Mobile Devices for Seamless External-Facing Biometric Matching

Saikrishna Badrinarayanan
Visa Research

Abstract:

We use biometrics to identify ourselves to our mobile devices everyday. Such authentication is internal-facing: we provide measurement on the same device where the template is stored. If our personal devices could participate in external-facing authentication too, where measurement is captured by a nearby external sensor, then we could also enjoy a frictionless authentication experience in a variety of physical spaces like grocery stores, convention centers, ATMs.

In this talk, I will discuss the design of a suite of secure protocols for external-facing authentication based on the cosine similarity metric which provides privacy for both user templates stored on their devices and the biometric measurement captured by external sensors. The protocols provide different levels of security, ranging from passive security with some leakage to active security with no leakage at all. With the help of new packing techniques and zero-knowledge proofs for Paillier encryption - and careful protocol design, these protocols achieve very practical performance numbers.

Talk based on joint work with Shashank Agrawal, Pratyay Mukherjee and Peter Rindal that was published at CCS 2020.

Biography:

Saikrishna Badrinarayanan is a Research Scientist in the Security team at Visa Research. He received his PhD in Computer Science from UCLA in 2019, where his work was supported by the IBM PhD Fellowship. His research interests are in Cryptography, Security, and Privacy. The focus of his PhD thesis was on building secure multiparty computation (MPC) protocols with optimal number of rounds of interaction. His current research focus is on MPC and its applications to various domains, including secure machine learning, private set intersection, and biometric authentication.