BATH, England — Here’s a frightening privacy warning courtesy of a British study: Simply picking up your smartphone and using apps can reveal your identity to outsiders. Scientists say that people can be identified based on the amount of time they spend on different apps. More than one in three people can be picked out by computer models based on their phone habits.
The research team out of the University of Bath and Lancaster University say the study has “worrying” implications for security and privacy. Experts there looked at phone data from 780 people. They then fed 4,680 days of app usage data into statistical models.
Each day was paired with one of the 780 users, so the model learned about users’ smartphone habits. They then tested whether people could be identified when the models were fed just a single day of anonymous data, which was not yet paired with a user.
Indeed, computers were able to identify users from the model — which were trained on only six days of app usage data per person — based on one day of anonymous data in a third of the cases. When the model predicted who the data belonged to, it could make a list of the most to least likely candidates. The model could see the top 10 most likely people a day’s worth of data belonged to, and in three quarters of cases, the correct user would be among the top ten candidates.
“In practical terms, a law enforcement investigation seeking to identify a criminal’s new phone from knowledge of their historic phone use could reduce a candidate pool of approximately 1,000 phones to ten phones, with a 25 percent risk of missing them,” says study author Paul Taylor, from Lancaster University, in a statement.
Software which is given access to someone’s standard activity logging means reasonable predictions can be made about who a user of a device is even when they are logged out. People can be identified without any monitoring of conversations or behaviors within apps themselves.
“We found that people exhibited consistent patterns in their application usage behaviors on a day-to-day basis, such as using Facebook the most and the calculator app the least. In support of this, we also showed that two days of smartphone data from the same person exhibited greater similarity in app usage patterns than two days of data from different people,” explains co-author Dr. Heather Shaw, a psychologist at Lancaster. “Therefore, it is important to acknowledge that app usage data alone, which is often collected by a smartphone automatically, can potentially reveal a person’s identity. While providing new opportunities for law enforcement, it also poses risks to privacy if this type of data is misused.”
The findings were published in the journal Psychological Science.
South West News Service writer Gwyn Wright contributed to this report.