Experimental identification of smartphones using fingerprints of built-in Micro-Electro Mechanical Systems (MEMS)

In this paper, we present the experimental evaluation of the identification of smartphones through their Inertial Measurement Units (IMUs). Tiny differences in the manufacturing process of the IMUs of the smartphones may determine unique patterns in the data output, which can be used to identify smartphones. In our study, three different phones of the same model are subject to repeatable movements (composing a repeatable scenario) using a high precision robotic arm. The measurements from accelerometers and gyroscope outputs for each repeatable scenario are collected and analyzed. The identification algorithm is based on the extraction of the statistical features of the collected data for each motion pattern. The features are used in a support vector machine classifier to identify the smartphone. The results of the evaluation are presented for different combination of features and IMU elements, which show that a high accuracy of identification more than 90% is possible.

BALDINI Gianmarco;  STERI Gary;  DIMC Franc;  GIULIANI Raimondo;  KAMNIK Roman; 

2016-08-04

MDPI AG

JRC100332

1424-8220,   

http://www.mdpi.com/1424-8220/16/6/818,    https://publications.jrc.ec.europa.eu/repository/handle/JRC100332,   

10.3390/s16060818,