FRIDAY, 12 JUNE 2015
The study, published in the Neurocomputing journal, saw researchers from Binghamton University study the brain signal patterns of 45 volunteers in response to 75 acronyms, such as DVD and FBI. The method focuses on semantic memory - responsible for concepts that are thought to be general knowledge, such as recognition of colour names or knowing what a dog is. While this type of memory is not generally associated with personal experiences, the authors of Brainprint proposed that the brain’s reaction would vary between people based on different familiarity with the letters listed. Using these reactions, a computer system was able to identify individuals with 94 percent accuracy.Sarah Laszlo, assistant professor of psychology and linguistics at Binghamton University, explains that brain biometrics offer an advantage over other methods, such as fingerprint or retina recognition, because they cannot be stolen by malicious methods and can be reset.
"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. 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," Laszlo said.
Although it is unlikely that this system will become widespread for low security applications in the near future, the use of brain signal recognition could prove useful for high-security locations where there are a small number of authorized users.
DOI: 10.1016/j.neucom.2015.04.025
Written by Raghd Rostom.
