TY - GEN
T1 - Prying into Private Spaces Using Mobile Device Motion Sensors
AU - Fyke, Zakery
AU - Griswold-Steiner, Isaac
AU - Serwadda, Abdul
N1 - Funding Information:
VII. ACKNOWLEDGMENT This research was supported by National Science Foundation Award Number: 1527795.
Publisher Copyright:
© 2019 IEEE.
PY - 2019/8
Y1 - 2019/8
N2 - Human made structures are designed in a predictable manner, conforming to the expectations of those who use them. These underlying patterns lend themselves to repetition in the way people get between different locations. We investigated the feasibility of an attacker using motion sensor data against their target, with the objective of predicting where they move and what activities they engaged in. In this work, we show that the gyroscope and accelerometer can be used to drive a privacy attack that stealthily maps out a user's private space with high accuracy. In particular, we show that a mobile app with access to this data can leverage it to analyze a user's step execution dynamics, turn operations, and general body movement activities and then methodically combine this information to map out paths and landmarks in protected spaces, such as houses. Using a dataset of 26 users who executed a number of activities and a combination of classification, regression, and distance matching techniques, we show this privacy attack to generate maps whose Normalized Hausdorff Distance from the ground-truth is as low as 0.1159.
AB - Human made structures are designed in a predictable manner, conforming to the expectations of those who use them. These underlying patterns lend themselves to repetition in the way people get between different locations. We investigated the feasibility of an attacker using motion sensor data against their target, with the objective of predicting where they move and what activities they engaged in. In this work, we show that the gyroscope and accelerometer can be used to drive a privacy attack that stealthily maps out a user's private space with high accuracy. In particular, we show that a mobile app with access to this data can leverage it to analyze a user's step execution dynamics, turn operations, and general body movement activities and then methodically combine this information to map out paths and landmarks in protected spaces, such as houses. Using a dataset of 26 users who executed a number of activities and a combination of classification, regression, and distance matching techniques, we show this privacy attack to generate maps whose Normalized Hausdorff Distance from the ground-truth is as low as 0.1159.
UR - http://www.scopus.com/inward/record.url?scp=85078764321&partnerID=8YFLogxK
U2 - 10.1109/PST47121.2019.8949056
DO - 10.1109/PST47121.2019.8949056
M3 - Conference contribution
AN - SCOPUS:85078764321
T3 - 2019 17th International Conference on Privacy, Security and Trust, PST 2019 - Proceedings
BT - 2019 17th International Conference on Privacy, Security and Trust, PST 2019 - Proceedings
A2 - Ghorbani, Ali
A2 - Ray, Indrakshi
A2 - Lashkari, Arash Habibi
A2 - Zhang, Jie
A2 - Lu, Rongxing
PB - Institute of Electrical and Electronics Engineers Inc.
Y2 - 26 August 2019 through 28 August 2019
ER -