High Accuracy and Presentation Attack Resistant Hand Authentication via Acoustic Sensing for Commodity Mobile Devices

Biometric authentication schemes, i.e., fingerprint and face authentication, raise serious privacy concerns. To alleviate such concerns, hand authentication has been proposed recently. Existing hand authentication schemes, however, use dedicated hardware, such as infrared or depth cameras, which are not available on commodity mobile devices. In this paper, we present EchoHand, a high accuracy and presentation attack resistant authentication scheme that complements camera-based 2-dimensional hand geometry recognition of one hand with an active acoustic sensing of the other hand. To this end, EchoHand plays an inaudible acoustic signal using the speaker to actively sense the holding hand and collects the echoes using the microphone. EchoHand does not rely on any specialized hardware but uses the built-in speaker, microphone and camera. EchoHand does not place more burdens on users than existing hand authentication methods. We conduct comprehensive experiments to evaluate the reliability, security, and usability of EchoHand. The results show that EchoHand has a low equal error rate of 2.45% with as few as 10 training data points and it defeats presentation attacks. The results of the user study also suggest that the required hand gestures are easy to perform, and EchoHand is very user-friendly with low latency.