🤖 AI Summary
This study addresses the limitation of traditional device authentication, which verifies identity only at unlock and fails to prevent unauthorized use after the legitimate user departs. Building upon the InsightFace framework, the authors introduce a time-based trust decay mechanism and present the first systematic comparison of continuous facial authentication performance across mobile and desktop platforms. The evaluation encompasses diverse device types, head poses, lighting conditions, and real-world usage scenarios. Through extensive video data collection and analysis under varied conditions, the study finds that device type has minimal impact on authentication performance; instead, increased false rejection rates in practice are primarily attributed to reduced facial visibility caused by occlusions or the user moving out of the camera’s field of view. These findings highlight a key challenge for deploying continuous authentication in real-world settings.
📝 Abstract
Personal devices hold sensitive data and provide access to sensitive services. Conventional personal device authentication verifies users' identity only at the moment access is granted. An unlocked device may be accessed by an unauthorized person if the user stops using the device without locking it, or if another person takes over. Continuous authentication addresses this gap. This paper investigates how device type and usage conditions influence continuous mobile face authentication with an InsightFace-based approach with temporal trust decay. We evaluate the approach with mobile and desktop recordings with different head directions and lighting conditions. We also evaluate recordings from everyday mobile device use without predefined tasks. The results show that device type alone has little impact, while different usage conditions do have impact on the authentication performance. Results also show that everyday mobile device use is in general more challenging for continuous face authentication, where reduced face visibility, including occlusions and faces outside the camera viewport, is a main contributor to false rejections.