COPPELL, Texas (CBSDFW.COM) – Does your smart phone know you as well as you think?
New technology is supposed to unlock some high-end smart phones by recognizing your face.
But two students at Coppell High School made a surprising discovery that raises questions about whether the technology works as well as it’s supposed to.
Apple says the odds of some random person unlocking an iPhone X with their face is a million to one.
Two unrelated students recorded a video of them doing it and it’s gotten Apple’s attention.
Umang Kaushik and Svayam Sharma surprised their classmates and themselves when the Coppell High School freshman first realized they could both unlock the same iPhone Xs with their faces.
“We’re not related and it’s kind of weird because we do look alike but our hair is different, we’re different, we’re not exactly like,” said Kaushik.
Their discovery is one of only a handful of documented examples that raise concerns about how secure smartphones that have the technology are.
The cameras on them send 30,000 infrared dots on a persons face to create a digital map of the user.
Tom Kulik is a technology and cyber security attorney and DFW.
He says there are ways to make the facial recognition work better.
“Train it,” said Kulik. “The more you use it the better it is and when you first set it up, actually test it against other family members, that’s actually a nice help because of certain similarities and features that might exist there.”
Here is what Apple provided CBS 11 in response to this story:
“The statistical probability is different for twins and siblings that look like you and among children under the age of 13, because their distinct facial features may not have fully developed. If you’re concerned about this, we recommend using a passcode to authenticate.”
Apple’s vice president of public policy for the Americas, Cynthia Hogan, made the following statement to Congress on Face ID:
“The accessibility of the product to people of diverse races and ethnicities was very important to us. Face ID uses facial matching neural networks that we developed using over a billion images, including IR and depth images collected in studies conducted with the participants’ informed consent. We worked with participants from around the world to include a representative group of people accounting for gender, age, ethnicity, and other factors. We augmented the studies as needed to provide a high degree of accuracy for a diverse range of users. In addition, a neural network that is trained to spot and resist spoofing defends against attempts to unlock your phone with photos or masks.”