Multi-Sensor-based Continuous Authentication of Smartphone Users with Two-Stage Feature Extraction

• Published in: IEEE internet of things journal p. 1
• Main Authors: Hu, Mingming, Zhang, Kun, You, Ruibang, Tu, Bibo
• Format: Journal Article
• Language: English
• Published: IEEE 2022
• Subjects: Accelerometers; Authentication; Behavioral biometrics; Behavioral sciences; Biometrics (access control); Continuous authentication; Deep metric learning; Feature extraction; Features fusion; Gyroscopes; Sensors
• DOI: 10.1109/JIOT.2022.3219135

The one-time authentication mechanism in traditional authentication methods cannot continuously authenticate smartphone users' identities throughout the session. Continuous authentication based on the behavioral biometrics recorded by the built-in sensors can solve this issue. However, the existing methods based on multi-sensor have poor ability to extract valuable features that can represent smartphone users' behavioral patterns. This article proposes a novel method combining the manual construction and the deep metric learning method to perform two-stage feature extraction respectively. We transform the time series raw data from three sensors (accelerometer, gyroscope, and magnetometer) into 69 statistical features in the first stage. Furthermore, unlike the existing serial features fusion methods, we innovatively fuse the constructed statistical features from three sensors into a three-channel matrix. Then, the fused features matrix with a three-channel is fed to the deep metric learning model for the second stage of feature extraction. And, we use the elliptic envelope algorithm to classify the user as a legitimate user or an impostor. Finally, we evaluate the performance of the proposed method on two public dataset. Experimental results show that our method can achieve an average accuracy of 99.71% and an average equal error rate (EER) of 0.56% on the HMOG dataset, and an average accuracy of 99.59% and an average equal error rate (EER) of 0.61% on the BrainRun dataset.