作者: Feng Yao , Suleiman Y. Yerima , BooJoong Kang , Sakir Sezer
关键词:
摘要: In order to protect user privacy on mobile devices, an event-driven implicit authentication scheme is proposed in this paper. Several methods of utilizing the for recognizing legitimate behavior are investigated. The investigated compute aggregate score and a threshold real-time determine trust level current using real data derived from interaction with device. designed to: operate completely background, require minimal training period, enable high recognition rate authentication, prompt detection abnormal activity that can be used trigger explicitly authenticated access control. paper, we investigate computation through standard deviation EWMA (exponentially weighted moving average) based algorithms. result extensive experiments collected over period several weeks Android phone indicates our approach feasible effective lightweight smartphones.