Tracking the human mobility using mobile device sensors

Takuya Watanabe, Mitsuaki Akiyama, Tatsuya Mori

    Research output: Contribution to journalArticle

    1 Citation (Scopus)

    Abstract

    We developed a novel, proof-of-concept side-channel attack framework called RouteDetector, which identifies a route for a train trip by simply reading smart device sensors: an accelerometer, magnetometer, and gyroscope. All these sensors are commonly used by many apps without requiring any permissions. The key technical components of RouteDetector can be summarized as follows. First, by applying a machine-learning technique to the data collected from sensors, RouteDetector detects the activity of a user, i.e., "walking," "in moving vehicle," or "other." Next, it extracts 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 and extensive simulation experiments using timetables and route maps for 9,090 railway stations of 172 railway companies.

    Original languageEnglish
    Pages (from-to)1680-1690
    Number of pages11
    JournalIEICE Transactions on Information and Systems
    VolumeE100D
    Issue number8
    DOIs
    Publication statusPublished - 2017 Aug 1

    Fingerprint

    Mobile devices
    Sensors
    Gyroscopes
    Magnetometers
    Accelerometers
    Application programs
    Learning systems
    Industry
    Experiments
    Side channel attack

    Keywords

    • Location identification
    • Mobile security
    • Side-channel attack

    ASJC Scopus subject areas

    • Software
    • Hardware and Architecture
    • Computer Vision and Pattern Recognition
    • Artificial Intelligence
    • Electrical and Electronic Engineering

    Cite this

    Tracking the human mobility using mobile device sensors. / Watanabe, Takuya; Akiyama, Mitsuaki; Mori, Tatsuya.

    In: IEICE Transactions on Information and Systems, Vol. E100D, No. 8, 01.08.2017, p. 1680-1690.

    Research output: Contribution to journalArticle

    Watanabe, Takuya ; Akiyama, Mitsuaki ; Mori, Tatsuya. / Tracking the human mobility using mobile device sensors. In: IEICE Transactions on Information and Systems. 2017 ; Vol. E100D, No. 8. pp. 1680-1690.
    @article{a11a590c24d1496abd2cc70343ae8211,
    title = "Tracking the human mobility using mobile device sensors",
    abstract = "We developed a novel, proof-of-concept side-channel attack framework called RouteDetector, which identifies a route for a train trip by simply reading smart device sensors: an accelerometer, magnetometer, and gyroscope. All these sensors are commonly used by many apps without requiring any permissions. The key technical components of RouteDetector can be summarized as follows. First, by applying a machine-learning technique to the data collected from sensors, RouteDetector detects the activity of a user, i.e., {"}walking,{"} {"}in moving vehicle,{"} or {"}other.{"} Next, it extracts 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 and extensive simulation experiments using timetables and route maps for 9,090 railway stations of 172 railway companies.",
    keywords = "Location identification, Mobile security, Side-channel attack",
    author = "Takuya Watanabe and Mitsuaki Akiyama and Tatsuya Mori",
    year = "2017",
    month = "8",
    day = "1",
    doi = "10.1587/transinf.2016ICP0022",
    language = "English",
    volume = "E100D",
    pages = "1680--1690",
    journal = "IEICE Transactions on Information and Systems",
    issn = "0916-8532",
    publisher = "Maruzen Co., Ltd/Maruzen Kabushikikaisha",
    number = "8",

    }

    TY - JOUR

    T1 - Tracking the human mobility using mobile device sensors

    AU - Watanabe, Takuya

    AU - Akiyama, Mitsuaki

    AU - Mori, Tatsuya

    PY - 2017/8/1

    Y1 - 2017/8/1

    N2 - We developed a novel, proof-of-concept side-channel attack framework called RouteDetector, which identifies a route for a train trip by simply reading smart device sensors: an accelerometer, magnetometer, and gyroscope. All these sensors are commonly used by many apps without requiring any permissions. The key technical components of RouteDetector can be summarized as follows. First, by applying a machine-learning technique to the data collected from sensors, RouteDetector detects the activity of a user, i.e., "walking," "in moving vehicle," or "other." Next, it extracts 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 and extensive simulation experiments using timetables and route maps for 9,090 railway stations of 172 railway companies.

    AB - We developed a novel, proof-of-concept side-channel attack framework called RouteDetector, which identifies a route for a train trip by simply reading smart device sensors: an accelerometer, magnetometer, and gyroscope. All these sensors are commonly used by many apps without requiring any permissions. The key technical components of RouteDetector can be summarized as follows. First, by applying a machine-learning technique to the data collected from sensors, RouteDetector detects the activity of a user, i.e., "walking," "in moving vehicle," or "other." Next, it extracts 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 and extensive simulation experiments using timetables and route maps for 9,090 railway stations of 172 railway companies.

    KW - Location identification

    KW - Mobile security

    KW - Side-channel attack

    UR - http://www.scopus.com/inward/record.url?scp=85026500387&partnerID=8YFLogxK

    UR - http://www.scopus.com/inward/citedby.url?scp=85026500387&partnerID=8YFLogxK

    U2 - 10.1587/transinf.2016ICP0022

    DO - 10.1587/transinf.2016ICP0022

    M3 - Article

    VL - E100D

    SP - 1680

    EP - 1690

    JO - IEICE Transactions on Information and Systems

    JF - IEICE Transactions on Information and Systems

    SN - 0916-8532

    IS - 8

    ER -