Apps may steal your data via location tracking

Smartphone users are unaware of privacy implications of some permissions they grant to apps and services and researchers have been able to identify which kind of personal information the apps extract with location tracking on.

This is the first extensive study shedding light on the range of personal information that can be inferred from location-tracking data.

Consequently, the study by two researchers from University of Bologna, Italy and Benjamin Baron from University College London, the UK also shows how collecting such information can represent a violation of the users' privacy.

To this end, the researchers developed a mobile application – TrackingAdvisor – that continuously collects user location.

From the location data, the app can extract personal information and asks users to give feedback on the correctness of such information as well as to rate its relevance in terms of privacy sensitivity.

“Users are largely unaware of the privacy implications of some permissions they grant to apps and services, in particular when it comes to location-tracking information”, said Mirco Musolesi from University of Bologna.

Thanks to machine learning techniques, these data provide sensitive information such as the place where users live, their habits, interests, demographics, and information about users’ personalities.

Through the TrackingAdvisor app employed in the study – published in Proceedings of the ACM on Interactive, Mobile, Wearable and Ubiquitous Technologies – researchers were able to identify which kind of personal information the app extracted and its privacy sensitivity according to users.

For the study, 69 users used TrackAdvisor for at least two weeks.

TrackAdvisor tracked more than 200,000 locations, identifying approximately 2,500 places and collecting almost 5,000 pieces of personal information concerning both demographics and personality.

Among the data gathered, the users find that the most sensitive pieces of information were the ones about health, socio-economic situation, ethnicity, and religion.

According to the researchers, analyses like this pave the way to designing targeted advertising systems that help users protect their privacy, especially with the data they deem more sensitive.