On-Device Voice Authentication with Paralinguistic Privacy

TL;DR

This paper presents a local, privacy-preserving voice authentication system that uses token-based credentials and liveness detection to verify users while safeguarding sensitive paralinguistic information, achieving high accuracy and fast performance.

Contribution

It introduces a novel on-device voice authentication framework combining token-based credentials, liveness detection, and customizable privacy filters, enhancing privacy and security in voice-based systems.

Findings

98.68% user verification accuracy

Runs in tens of milliseconds on standard hardware

Effectively filters raw voice data according to user privacy preferences

Abstract

Using our voices to access, and interact with, online services raises concerns about the trade-offs between convenience, privacy, and security. The conflict between maintaining privacy and ensuring input authenticity has often been hindered by the need to share raw data, which contains all the paralinguistic information required to infer a variety of sensitive characteristics. Users of voice assistants put their trust in service providers; however, this trust is potentially misplaced considering the emergence of first-party 'honest-but-curious' or 'semi-honest' threats. A further security risk is presented by imposters gaining access to systems by pretending to be the user leveraging replay or 'deepfake' attacks. Our objective is to design and develop a new voice input-based system that offers the following specifications: local authentication to reduce the need for sharing raw voice data, local privacy preservation based on user preferences, allowing more flexibility in integrating such a system given target applications privacy constraints, and achieving good performance in these targeted applications. The key idea is to locally derive token-based credentials based on unique-identifying attributes obtained from the user's voice and offer selective sensitive information filtering before transmitting raw data. Our system consists of (i) 'VoiceID', boosted with a liveness detection technology to thwart replay attacks; (ii) a flexible privacy filter that allows users to select the level of privacy protection they prefer for their data. The system yields 98.68% accuracy in verifying legitimate users with cross-validation and runs in tens of milliseconds on a CPU and single-core ARM processor without specialized hardware. Our system demonstrates the feasibility of filtering raw voice input closer to users, in accordance with their privacy preferences, while maintaining their authenticity.