Hickson, whose
LinkedIn profile
identifies him as a graduate research assistant at Georgia Tech focused
on computer vision and robotics, broadcasted his methods on his blog
Wednesday. Basically, Hickson took an image of Snapchat's logo, then
built a program that can identify certain points on the logo and match
them to the images in the test.
"With very little effort, my code was able to "find the ghost" in the
above example with 100% accuracy," Hickson wrote. "I'm not saying it is
perfect, far from it. I'm just saying that if it takes someone less
than an hour to train a computer to break an example of your human
verification system, you are doing something wrong."
The security hack suggests another misstep for Snapchat, which dealt with a more severe hack earlier this year
when 4.6 million accounts and phone numbers were leaked online. That hack occurred after a security firm had warned Snapchat about the potential for a security breach.
Hickson included the hack code
on Github. His blog was another message to the company that it needs to beef up security.
a Snapchat spokesperson
responded: "We continue to make significant progress in our efforts to
secure Snapchat. For security reasons, we cannot provide detailed
information on security countermeasures."