Document Type
Article
Publication Date
1-2020
DOI
10.1016/j.pmcj.2019.101106
Publication Title
Pervasive and Mobile Computing
Volume
61
Issue
SI
Pages
101106 (16 pp.)
Abstract
This paper reports a new side-channel attack to smartphones using the unrestricted magnetic sensor data. We demonstrate that attackers can effectively infer the Apps being used on a smartphone with an accuracy of over 80%, through training a deep Convolutional Neural Networks (CNN). Various signal processing strategies have been studied for feature extractions, including a tempogram based scheme. Moreover, by further exploiting the unrestricted motion sensor to cluster magnetometer data, the sniffing accuracy can increase to as high as 98%. To mitigate such attacks, we propose a noise injection scheme that can effectively reduce the App sniffing accuracy to only 15% and at the same time has a negligible effect on benign Apps. ©2019 Published by Elsevier B.V.
Original Publication Citation
Ning, R., Wang, C., Xin, C. S., Li, J., & Wu, H. Y. (2020). DeepMag+: Sniffing mobile apps in magnetic field through deep learning. Pervasive and Mobile Computing, 61, 101106. doi:10.1016/j.pmcj.2019.101106
Repository Citation
Ning, Rui; Wang, Cong; Xin, ChunSheng; Li, Jiang; and Wu, Hongyi, "DeepMag+ : Sniffing Mobile Apps in Magnetic Field Through Deep Learning" (2020). Electrical & Computer Engineering Faculty Publications. 236.
https://digitalcommons.odu.edu/ece_fac_pubs/236
Included in
Databases and Information Systems Commons, Digital Communications and Networking Commons
Comments
©2019 Published by Elsevier B.V.
Funding agencies: Office of Naval Research and National Science Foundation (NSF).
Grant numbers: CNS-1528004, CNS-1659795, CNS-1745632, CNS-1828593, EEC-1840458, OAC-1829771