Privacy Preserving Biometrics-Based and User Centric Authentication Protocol

We propose a privacy preserving biometrics-based authentication protocol by which users can authenticate to different service providers from their own devices without involving identity providers in the transactions. Authentication is performed through a zero-knowledge proof of knowledge protocol which is based on a cryptographic identity token created using the unique, repeatable and revocable biometric identifier of the user and a secret provided by the user which enables two-factor authentication as well. Our approach for generating biometric identifiers from the user's biometric image is based on the support vector machine classification technique in conjunction with a mechanism for feature extraction from the biometric image. The paper includes experimental results on a dataset of iris images and a security and privacy analysis of the protocol.