Study: Brain Signals Show Promise as Biometric Authentication Method
June 8, 2015
University researchers in New York are studying how brain signals could serve as a biometric authentication method to replace passwords. A team from Binghamton University in Binghamton, N.Y. recently published a study in the academic journal Neurocomputing in which they observed the brain signals of volunteers as they read a list of words. The way each volunteer’s brain reacted to a list of spoken words was different enough that the scientists could successfully identify a specific person with 94 percent accuracy.
The reason “brainprints,” as the research team has dubbed them, are exciting is that they can be “reset.” While biometrics increasingly are being used to authenticate users in account-opening environments, one drawback has always been the fear of what happens if, say, a fingerprint, is compromised by hackers. A person’s fingerprint can’t be changed. Brainprints may address this problem because if you introduce new keywords, according to the research, different brain signals result.
According to Sarah Laszlo, assistant professor of psychology and linguistics at Binghamton University and co-author of the paper, brain biometrics are appealing because they are cancellable and cannot be stolen by malicious means the way a finger or retina can.
“If someone’s fingerprint is stolen, that person can’t just grow a new finger to replace the compromised fingerprint—the fingerprint for that person is compromised forever,” said Laszlo. “Fingerprints are ‘non-cancellable.’ Brainprints, on the other hand, are potentially cancellable. So, in the unlikely event that attackers were actually able to steal a brainprint from an authorized user, the authorized user could then ‘reset’ their brainprint.”