A report on personally identifiable sensor data from smartphone devices

Abstract

An average smartphone is equipped with an abundance of sensors to provide a variety of vital functionalities and conveniences. The data from these sensors can be collected in order to find trends or discover interesting correlations in the data but can also be used by nefarious entities for the purpose of revealing the identity of the persons who generated this data.In this paper, we seek to identify what types of sensor data can be collected on a smartphone and which of those types can pose a threat to user privacy by looking into the hardware capabilities of modern smartphone devices and how smartphone data is used in the literature. We then summarize some implications that this information could have on the GDPR.

17 pages, 5 tables, parts of this paper were used in the PhD thesis by the same author available at https://archive-ouverte.unige.ch/unige:112869

References in corpus (6)

• Touchalytics: On the Applicability of Touchscreen Input as a Behavioral Biometric for Continuous Authentication
• PlaNet - Photo Geolocation with Convolutional Neural Networks
• Mobile Device Identification via Sensor Fingerprinting
• Data Driven Authentication: On the Effectiveness of User Behaviour Modelling with Mobile Device Sensors
• Predicting Floor-Level for 911 Calls with Neural Networks and Smartphone Sensor Data
• Mobile phone identification through the built-in magnetometers