DynamicLip: Shape-Independent Continuous Authentication via Lip Articulator Dynamics

TL;DR

This work tackles the privacy and robustness limitations of traditional biometrics by introducing DynamicLip, a shape-independent continuous authentication system based on lip articulator dynamics. It builds a three-tier feature hierarchy (static shape, texture, and dynamic articulator cues) and leverages a Siamese network to measure cross-sample similarity, enabling reliable authentication even as lips transition between static and speaking states. The system demonstrates 99.06% accuracy on a 50-subject dataset and shows strong resistance to mimic, advanced mimic, and AI deepfake attacks, underscoring its viability for privacy-conscious, hands-free applications in VR and smart devices. Its reliance on standard smartphone cameras and resilience to lighting, angle, and lip condition variations further attests to its practical impact for secure, continuous biometric authentication.

Abstract

Biometrics authentication has become increasingly popular due to its security and convenience; however, traditional biometrics are becoming less desirable in scenarios such as new mobile devices, Virtual Reality, and Smart Vehicles. For example, while face authentication is widely used, it suffers from significant privacy concerns. The collection of complete facial data makes it less desirable for privacy-sensitive applications. Lip authentication, on the other hand, has emerged as a promising biometrics method. However, existing lip-based authentication methods heavily depend on static lip shape when the mouth is closed, which can be less robust due to lip shape dynamic motion and can barely work when the user is speaking. In this paper, we revisit the nature of lip biometrics and extract shape-independent features from the lips. We study the dynamic characteristics of lip biometrics based on articulator motion. Building on the knowledge, we propose a system for shape-independent continuous authentication via lip articulator dynamics. This system enables robust, shape-independent and continuous authentication, making it particularly suitable for scenarios with high security and privacy requirements. We conducted comprehensive experiments in different environments and attack scenarios and collected a dataset of 50 subjects. The results indicate that our system achieves an overall accuracy of 99.06% and demonstrates robustness under advanced mimic attacks and AI deepfake attacks, making it a viable solution for continuous biometric authentication in various applications.

Figures (22)

• Figure 1: Core idea of the proposed system.
• Figure 2: System flow of the proposed system.
• Figure 3: The lip region formed by 20 landmarks (point 48 to 67).
• Figure 4: Dynamic lip biometric feature hierarchy.
• Figure 5: Region of Interest (ROI). (a) Cropped and scaled ROI. (b) Barbarized ROI.