"How Picking Up Your Smartphone Could Reveal Your Identity"

How much time an individual spends on different smartphone apps is enough to identify them in a larger group in more than one in three cases, according to researchers warning of the implications for security and privacy. The researchers analyzed smartphone data from 780 people. They loaded 4,680 days of app usage data into statistical models, with each day being paired with one of the 780 users so that the models can learn the individuals' daily app use patterns. Then the researchers tested whether the models could identify an individual when fed only a single day of smartphone activity that was anonymous and not yet paired with a user. The models, which were trained on only six days of app usage data per individual, were able to identify the correct person from a day of anonymous data one-third of the time. The models could also list the most to least likely candidates when predicting who owns the data. The list provided when the models made a prediction showed the top 10 most likely individuals that a specific day of data belonged to, and nearly 75 percent of the time, the correct user would be among that top 10. The researchers warn that software granted access to a smartphone's standard activity logging could generate a reasonable prediction about the identity of the user even if they are logged out of their account. Identification is still possible without the monitoring of conversations or behaviors within apps themselves. This article continues to discuss the study on how app usage data can reveal a person's identity. 

Lancaster University reports "How Picking Up Your Smartphone Could Reveal Your Identity"