App grabs personal data using facial recognition

Posted by Kate Taylor

Carnegie Mellon University researchers say they can identify strangers on the internet using just one photo - and even predict part of their social security number.

"A person's face is the veritable link between her offline and online identities," says Carnegie Mellon CyLab researcher Alessandro Acquisti.

"When we share tagged photos of ourselves online, it becomes possible for others to link our face to our names in situations where we would normally expect anonymity."

The team used off-the-shelf face recognizer PittPatt - now owned by Google - along with cloud computing and publicly available information from social network sites to identify individuals online and offline.

In one experiment, they identified individuals on a popular online dating site where members protect their privacy through pseudonyms. In another, they identified students walking on campus, simply through their profile photos on Facebook.

In a third experiment, the research team predicted personal interests and, in some cases, even part of their Social Security numbers, using only a photo of their faces. They were able to do this in cases where a person had their date of birth and city posted on Facebook.

They've even built a smartphone app that can do all this in real-time, overlaying personal and private information on the target's face on the phone's screen.

"The seamless merging of online and offline data that face recognition and social media make possible raises the issue of what privacy will mean in an augmented reality world," Acquisti said.

"Ultimately, all this access is going to force us to reconsider our notions of privacy."