New Security System Developed to Make Mobile Devices More Secure

A team of cybersecurity researchers has developed a novel security system for cell phones that locks the device if the user's taps and swipes don't match that of the owner.

Researchers at the Georgia Institute of Technology have come up with a new security system for cell phones much more advanced than the simple password, gesture and fingerprint system of security. They have come up with a new system called 'LatentGesture' that continuously monitors the owner's taps and swipes. If the user's taps don't match that of the owners' then the new system identifies these differences and immediately locks the device.

"The system learns a person's 'touch signature,' then constantly compares it to how the current user is interacting with the device," Polo Chau, a Georgia Tech College of Computing assistant professor who led the study, said in a statement.

The new system was used in a lab study using Android devices.  To test the system the researchers set up an electronic form with several tasks listed for 20 subjects. These subjects were asked to tap the button, check boxes and slide bars on the phone and tablet in order to fill the form.  This system accurately tracked the user's tendencies and created a profile of each.  These profiles were stored and one person's signature was designated as the owner of the device the tests were conducted again.  The system identified the owner and also traced the unauthorized users.  

"Just like your fingerprint, everyone is unique when they use a touchscreen," said Chau. "Some people slide the bar with one quick swipe. Others gradually move it across the screen. Everyone taps the screen with different pressures while checking boxes."

Apart from this, the system is also programmed to store five touch signatures on one device. This includes one owner and four other authorized users.  The system was 98 percent accurate in identifying the owner on a Smartphone and 97 percent accurate on tablets.

"This feature could be used when a child uses her dad's tablet," said College of Computing sophomore Premkumar Saravanan. "The system would recognize her touch signature and allow her to use the device. But if she tried to buy an app, the system could prevent it."

This research will be presented in Toronto at the ACM Chinese CHI 2014 from April 26 to 27 and is supported by the National Science Foundation (NSF).