Facebook's online privacy woes are well-known. But here's an offline one: its large database of profile photos can be victimised to determine you as you're travel walking the street.
A Carnegie Mellon University researcher today described how he built a database of nearly 25,000 photographs expropriated from students' Facebook profiles. Then he set up a desk in one of the campus buildings and asked few volunteers to peep into Webcams.
The results: face recognition software put a name to the face of 31 percent of the students after, on come, lower than trey seconds of rapid-fire comparisons.
In a few years, "facial visual searches may be as popular as today's text-based searches," says Alessandro Acquisti, who presented his development in cooperation with Ralph Receipts and Fred Stutzman at the Black Hat computer conference.
As a check of idea, the Carnegie Mellon researchers also formed an iPhone app that can position a exposure of someone, piping it through facial recognition software, and then exhibit on-screen that person's canvas and essential statistics.
Few of the professor from Carnegie Mellon University belive that this could be an ominous risks for privacy of any individual.
In another test researchers compared 277,978 Facebook profiles against nearly 6,000 profiles extracted from an unnamed dating Web site. Here also the success rate of software was 40 percent match. Funniest part in this tests are, almost 1 in 10 of the dating site's members--nearly all of whom used pseudonyms--turned out to be identifiable name. Now, this can be a risk for guys dating multiple girls.
Facial recognition technology, which has been developing in labs for decades, is finally going mainstream. Face.com opened its doors to developers last year; the technology is built into Apple's Aperture software and Flickr. Google bought a face-recognition technology in the last few weeks, and Facebook's automated photo-tagging has drawn privacy scrutiny.
Acquisti is the first to admit that the technology isn't perfect. It works best with frontal face photos, not ones taken at an angle. The larger the database becomes, the more time comparisons take, and the more false-positive errors arise.
On the other hand, face recognition technology is advancing quickly, especially for nonfrontal photos. "What we did on the street with mobile devices today will be accomplished in less intrusive ways tomorrow," he says. "A stranger could know your last tweet just by looking at you."
Read more here