Understanding the threats caused by correlating human mobility and smart device sensors

2016 Fiscal Year Final Research Report

• Project/Area Number: 15K12038
• Research Category: Grant-in-Aid for Challenging Exploratory Research
• Allocation Type: Multi-year Fund
• Research Field: Information security
• Research Institution: Waseda University
• Principal Investigator: Mori Tatsuya 早稲田大学, 理工学術院, 准教授 (60708551)
• Research Collaborator: WATANABE Takuya ; AKIYAMA Mitsuaki ; YAGI Takeshi
• Project Period (FY): 2015-04-01 – 2017-03-31
• Keywords: センサー / セキュリティ / プライバシー / 機械学習

Outline of Final Research Achievements

We verified the feasibility of a proof-of-concept side-channel attack that identifies a route for a train trip by simply reading smart device sensors: an accelerometer, magnetometer, and gyroscope, which are commonly used by many apps without requiring any permissions. First, by applying a machine-learning technique to the data collected from sensors, we can detect the activity of a user, i.e., walking, in moving vehicle, or other. Next, we extract departure/arrival times of vehicles from the sequence of the detected human activities. Finally, by correlating the detected departure/arrival times of the vehicle with timetables/route maps collected from all the railway companies in the rider’s country, it identifies potential routes that can be used for a trip. We demonstrate that the strategy is feasible through field experiments. Building wrapper APIs that provide many useful functions, while hiding raw data, is a promising approach to thwart sensor-based side-channel attacks.

Free Research Field

情報セキュリティ・プライバシー