Although biometric security, like FaceID or fingerprint readers seems like an extremely secure way of protecting devices, it still has its flaws and with criminals increasingly using machine learning to break into devices, something needs to be done to boost its security.
Enter Real Time Capture – an extra layer of security that uses a challenge only humans can complete to make the method ultra-secure. To unlock a device, the human must look at a camera and answer a randomly-selected question to answer within a very short time frame.
Making sure the timeframe is too short for AI or machine learning to process is key, researchers at the Georgia Institute of Technology explained.
“The attackers now know what to expect with authentication that asks them to smile or blink, so they can produce a blinking model or smiling face in real time relatively easily,” said Erkam Uzun, a graduate research assistant in Georgia Tech’s School of Computer Science and the paper’s first author.
“We are making the challenge harder by sending users unpredictable requests and limiting the response time to rule out machine interaction.”
In trials of the technology, humans were able to respond to the question in a second or less, compared to between six and ten seconds by machine. If it takes longer than a few seconds for the question to be answered, the subject will not be allowed entry.
In all, there will be four steps for the human to answer in order to gain access. They will need to answer a question from a Captcha, answer in a very short time frame and their facial features and voice must match the owner’s.
“Using face recognition alone for authentication is probably not strong enough,” Wenke Lee, a professor in Georgia Tech’s School of Computer Science and co-director of the Georgia Tech Institute for Information Security and Privacy said. “We want to combine that with Captcha, a proven technology. If you combine the two, that will make face recognition technology much stronger.”
