Open AccessA Contactless Authentication System Based on WiFi CSI
Author(s) -
Chi Lin,
Pengfei Wang,
Chuanying Ji,
Mohammad S. Obaidat,
Lei Wang,
Guowei Wu,
Qiang Zhang
Publication year - 2023
Publication title -
acm transactions on sensor networks
Language(s) - English
Resource type - Journals
SCImago Journal Rank - 0.598
H-Index - 67
eISSN - 1550-4867
pISSN - 1550-4859
DOI - 10.1145/3532095
Subject(s) - computer science , authentication (law) , sensitivity (control systems) , artificial intelligence , transfer of learning , signal (programming language) , identity (music) , residual , transfer (computing) , wireless sensor network , human–computer interaction , real time computing , machine learning , pattern recognition (psychology) , computer vision , computer security , computer network , electronic engineering , algorithm , physics , programming language , parallel computing , acoustics , engineering
The ubiquitous and fine-grained features of WiFi signals make it promising for realizing contactless authentication. Existing methods, though yielding reasonably good performance in certain cases, are suffering from two major drawbacks: sensitivity to environmental dynamics and over-dependence on certain activities. Thus, the challenge of solving such issues is how to validate human identities under different environments, even with different activities. Towards this goal, in this paper, we develop WiTL, a transfer learning-based contactless authentication system, which works by simultaneously detecting unique human features and removing the environment dynamics contained in the signal data under different environments. To correctly detect human features (i .e ., human heights used in this paper), we design a Height Estimation Algorithm (HES) based on Angle of Arrival (AoA). Furthermore, a transfer learning technology combined with the Residual Network (ResNet) and the adversarial network is devised to extract activity features and learn environmental independent representations. Finally, experiments through multi-activities and under multi-scenes are conducted to validate the performance of WiTL. Compared with the state-of-the-art contactless authentication systems, WiTL achieves promising a great accuracy over 93% and 97% in multi-scenes and multi-activities identity recognition, respectively.