EchoLive: Acoustic-Based 3D Dynamic Face Authentication
Zheng Zheng, Jianyu Wu, Siyang Zhu, Cong Wang, Yue Zhao, Qian Wang · 2024
Face authentication has become prevalent in our daily lives. However, mainstream vision-based face authentication systems suffer from some limitations, including poor performance in dark environments, vulnerability to spoofing attacks, and privacy concerns. This paper proposes EchoLive, an acoustic-based 3D dynamic face authentication system that leverages acoustic sensors on mobile devices to sense the 3D dynamic facial cues for authentication. It utilizes the speaker to emit ultrasonic acoustic signals and the microphone to receive the echo signals from the user's face. From the echo signals, we can extract users' unique 3D facial geometry and dynamic facial information (i.e., head movements) and then perform reliable and secure 3D dynamic authentication. Utilizing acoustic sensing technology, EchoLive exhibits robustness under various environmental lighting and noise conditions, providing strong security guarantees and alleviating user concerns about the privacy of visual facial data. Extensive experiments show that EchoLive can realize reliable 3D dynamic face authentication and defend against mainstream spoofing attacks well.