2017/08/30 by Wei‐Han Lee, Xiaochen Liu, Lee, Wei-Han +7
Computer Science · #Biometric Identification and Security #Cryptography and Security (cs.CR) #FOS: Computer and information sciences #Innovative Human-Technology Interaction #User Authentication and Security Systems
paper · pdf · doi:10.48550/arxiv.1708.09366
openalex publication_date 2017/08/30 · openalex created_date 2025/10/10 · openalex updated_date 2026/07/28
We propose Secure Pick Up (SPU), a convenient, lightweight, in-device,\nnon-intrusive and automatic-learning system for smartphone user authentication.\nOperating in the background, our system implicitly observes users' phone\npick-up movements, the way they bend their arms when they pick up a smartphone\nto interact with the device, to authenticate the users.\n Our SPU outperforms the state-of-the-art implicit authentication mechanisms\nin three main aspects: 1) SPU automatically learns the user's behavioral\npattern without requiring a large amount of training data (especially those of\nother users) as previous methods did, making it more deployable. Towards this\nend, we propose a weighted multi-dimensional Dynamic Time Warping (DTW)\nalgorithm to effectively quantify similarities between users' pick-up\nmovements; 2) SPU does not rely on a remote server for providing further\ncomputational power, making SPU efficient and usable even without network\naccess; and 3) our system can adaptively update a user's authentication model\nto accommodate user's behavioral drift over time with negligible overhead.\n Through extensive experiments on real world datasets, we demonstrate that SPU\ncan achieve authentication accuracy up to 96.3% with a very low latency of 2.4\nmilliseconds. It reduces the number of times a user has to do explicit\nauthentication by 32.9%, while effectively defending against various attacks.\n