Researchers Analyze Brainwaves To Authenticate Users

It sounds like something straight out of science fiction: brainwaves taking the place of passwords in the name of authentication. But a new study by researchers from the U.C. Berkeley School of Information is turning fiction into reality.

The study (PDF) examined the brainwave signals of individuals performing specific actions to see whether they can be consistently matched to the right individual. To do this, the researchers recruited 15 college students to participate, asking them to allow their brainwaves to be recorded as they performed a series of repeatable tasks. Three were tasks everyone was asked to do, while four were ones where the users had individual secrets.

In the tasks where participants could choose a personal secret, they were asked to imagine performing a repetitive motion from a sport of their choice, singing a song of their choice, watching a series of on-screen images and silently counting the objects that match a color of their choice, or choose their own thought and focus on it for 10 seconds.

To measure the subjects' brainwaves, the team used the NeuroSky Mindset, a Bluetooth headset that records Electroencephalographic (EEG) activity. In the end, the team was able to match the brainwave signals with 99 percent accuracy.

"We are not trying to trace back from a brainwave signal to a specific person," explains Prof. John Chuang, who led the team. "That would be a much more difficult problem. Rather, our task is to determine if a presented brainwave signal matches the brainwave signals previously submitted by the user when they were setting up their pass-thought."

"In this case," he continues, "our experimental study found that we can with high accuracy make the determination whether a presented brainwave signal belongs to a user or not due to patterns in the brainwaves that are different for different individuals. We also found that it was not necessary to have users perform different mental tasks in order to achieve our level of authentication accuracy. Having our experimental subjects perform different mental tasks allows us to study whether certain types of tasks were preferred by users because of their enjoyability or ease of execution."

The team's findings were presented at the 17th International Conference on Financial Cryptography and Data Security in Japan this week. In a paper, the team argues that the embedding of EEG sensors in wireless headsets and other consumer electronics makes authenticating users based on their brainwave signals a realistic possibility.

"Obviously, using brainwaves for authentication [has been] the stuff of science-fiction for a very long time," Chuang says. "There [have] been a number of previous research studies looking at brainwave authentication, but they employ multichannel EEG technology in clinical settings. When the NeuroSky single-channel technology became available on the market, we decided to study whether brainwave authentication is feasible with these inexpensive consumer-grade devices in everyday [nonclinical] settings."

Have a comment on this story? Please click "Add Your Comment" below. If you'd like to contact Dark Reading's editors directly, send us a message.