PowerSpy: Location Tracking using Mobile Device Power Analysis

Abstract

Modern mobile platforms like Android enable applications to read aggregate power usage on the phone. This information is considered harmless and reading it requires no user permission or notification. We show that by simply reading the phone's aggregate power consumption over a period of a few minutes an application can learn information about the user's location. Aggregate phone power consumption data is extremely noisy due to the multitude of components and applications that simultaneously consume power. Nevertheless, by using machine learning algorithms we are able to successfully infer the phone's location. We discuss several ways in which this privacy leak can be remedied.

Usenix Security 2015

References in corpus (2)

• Mobile Device Identification via Sensor Fingerprinting
• We Can Track You If You Take the Metro: Tracking Metro Riders Using Accelerometers on Smartphones

Cited by in corpus (11)

• AttriGuard: A Practical Defense Against Attribute Inference Attacks via Adversarial Machine Learning
• PinMe: Tracking a Smartphone User around the World
• Multi-label Methods for Prediction with Sequential Data
• VindiCo: Privacy Safeguard Against Adaptation Based Spyware in Human-in-the-Loop IoT
• Defending against Machine Learning based Inference Attacks via Adversarial Examples: Opportunities and Challenges
• Addressing Security and Privacy Challenges in Internet of Things
• Maya: Falsifying Power Sidechannels with Dynamic Control
• Privacy Inference Attacks and Defenses in Cloud-based Deep Neural Network: A Survey
• Game-Theoretic Model of Incentivizing Privacy-Aware Users to Consent to Location Tracking
• Mitigating Location Privacy Attacks on Mobile Devices using Dynamic App Sandboxing
• Who Is Charging My Phone? Identifying Wireless Chargers via Fingerprinting