Quickest Multiple User Active Authentication Pramuditha Perera, Julian Fierrez, and Vishal M. Patel Abstract In this chapter, we investigate how to detect intruders with low latency for Active Authentication (AA) systems with multiple-users. We extend The Quickest Change Detection (QCD) framework is extended to the multiple-user case and the Multiple-user Quickest Intruder Detection (MQID) algorithm is formulated. Furthermore, the algorithm is extended to the data-efficient scenario where intruder detection is carried out with fewer observation samples. The effectiveness of the method is evaluated on two publicly available AA datasets on the face modality. 1 Introduction Balancing the trade-offs between security and usability is one of the major challenges in mobile security [4]. Longer passwords with a combination of digits, letters and special characters are known to be secure but they lack usability in the mobile applications. On the other hand, swipe patterns, face verification and fingerprint verification have emerged as popular mobile authentication methods owing to the ease of use they provide. However, security of these methods are challenged due to different types of attack mechanisms employed by intruders ranging from simple shoulder attacks to specifically engineered spoof attacks. In this context, Active Authentication (AA), where the mobile device user is continuously P. Perera Department of Electrical and Computer Engineering, Johns Hopkins University, Baltimore, MD, USA e-mail: pperera3@jhu.edu J. Fierrez School of Engineering, Universidad Autonoma de Madrid, Madrid, Spain e-mail: julian.fierrez@uam.es V. M. Patel () Department of Electrical Engineering, Johns Hopkins University, Baltimore, MD, USA e-mail: vpatel36@jhu.edu © Springer Nature Switzerland AG 2020 T. Bourlai et al. (eds.), Securing Social Identity in Mobile Platforms, Advanced Sciences and Technologies for Security Applications, https://doi.org/10.1007/978-3-030-39489-9_10 179