LIPAuth : Hand-dependent Light Intensity Patterns for Resilient User Authentication

Abstract

Authentication mechanisms deployed on access control systems undertake the responsibility of judging user identity, to prevent unauthorized individuals from illegally approaching. In this paper, we propose LIPAuth leveraging hand-dependent L ight I ntensity P attern to Auth enticate users. To be specific, lights released by a screen, are blocked and reflected by one hand above it; in this propagation process, hands exhibit user-specific ability in driving light absorption and attenuation due to owning unique structures, thereby outputting discriminative intensity patterns representing user identity. To implement LIPAuth , we first study the effects of screen contents on light intensity to elaborately design its patterns embedding enough hand structure biometrics. We then design a customized dynamic stimulus-response mechanism for LIPAuth  and make it resilient to the risks of potential registration profile leakage. Subsequently, we construct a joint pipeline consisting of signal processing and a learning-based generative adversarial network to overcome interference from variable user behaviors. More importantly, LIPAuth  just utilizes common sensors to capture light signals hence achieving low cost. We finally conduct extensive experiments in three scenarios to evaluate the authentication performance of LIPAuth  prototype.