ZK-SERIES: Privacy-Preserving Authentication using Temporal Biometric Data

Abstract

Biometric authentication relies on physiological or behavioral traits that are inherent to a user, making them difficult to lose, forge or forget. Biometric data with a temporal component enable the following authentication protocol: recent readings of the underlying biometrics are encoded as time series and compared to a set of base readings. If the distance between the new readings and the base readings falls within an acceptable threshold, then the user is successfully authenticated. Various methods exist for comparing time series data, such as Dynamic Time Warping (DTW) and the Time Warp Edit Distance (TWED), each offering advantages and drawbacks depending on the context. Moreover, many of these techniques do not inherently preserve privacy, which is a critical consideration in biometric authentication due to the complexity of resetting biometric credentials. In this work, we propose ZK-SERIES to provide privacy and efficiency to a broad spectrum of time series-based authentication protocols. ZK-SERIES uses the same building blocks, i.e., zero-knowledge multiplication proofs and efficiently batched range proofs, to ensure consistency across all protocols. Furthermore, it is optimized for compatibility with low-capacity devices such as smartphones. To assess the effectiveness of our proposed technique, we primarily focus on two case studies for biometric authentication: shake-based and blow-based authentication. To demonstrate ZK-SERIES's practical applicability even in older and less powerful smartphones, we conduct experiments on a 5-year-old low-spec smartphone using real data for two case studies alongside scalability assessments using artificial data. Our experimental results indicate that the privacy-preserving authentication protocol can be completed within 1.3 seconds on older devices.