Inferring User Routes and Locations Using Zero-Permission Mobile Sensors

Explore a conference talk that delves into the security implications of inferring user routes and locations using zero-permission mobile sensors. Learn about a novel approach to modeling this problem as a maximum likelihood route identification on a graph generated from OpenStreetMap data. Discover how gyroscope, accelerometer, and magnetometer information can be used to infer vehicular users' location and traveled routes with high accuracy, without explicit user authorization. Examine the results of extensive simulations across 11 cities and real driving experiments in Boston and Waltham, Massachusetts, highlighting the potential privacy risks associated with mobile sensor data. Gain insights into the challenges, evaluation metrics, and implications of this research for mobile device security and user privacy.

Motivation
Outline
Approach
Map Data Graph Construction
Challenges
Sensor Data Route Construction
Scoring
Evaluation Metric - Gyroscope Accuracy
Cities for Simulation
Creating Simulation Routes
Evaluation Metric - Real Driving Routes
Summary
Thank You