Your 'brainprint' can identify you with 100% accuracy

A biometric "brainprint" system can identify people with 100 per cent accuracy based on the results of an electroencephalogram (EEG) recording of their brain activity, Binghamton University has found. 

The US team recorded the brain activity of 50 people as they looked at a series of 500 images, including: "a slice of pizza, a boat, Anne Hathaway, the word 'conundrum'." Each participant's brain reacted differently to the images, and as a result, the team's computer system was able to identify every brainprint with complete accuracy.

"When you take hundreds of these images, where every person is going to feel different about each individual one, then you can be really accurate in identifying which person it was who looked at them just by their brain activity," study lead Sarah Laszlo said. 

The researchers' latest paper, CEREBRE: A Novel Method for Very High Accuracy Event-Related Potential Biometric Identification, published in IEEE Transactions on Information Forensics and Security, details the results of their improvements to the brainprint method, as well as potential uses of brainprint technology for identification in high-security environments

A brainprint would be recorded by having a user look at an image while hooked up to an electroencephalograph that would record their brain activity in response to the stimulus – setting the password. On future occasions, the user's identity would be confirmed by exposing them to the stimulus again, recording their response and using pattern classifying computer systems to compare the results.

While such a system would be necessity be more involved, potentially slower and more expensive than many rival biometric identification methods, its reliance on specific stimuli presents some unique advantages. As Laszlow observes: "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."
A previous experiment, documented in a paper published in Neurocomputing used similar comparative methods, but had participants read a block of text, instead of using images.
The earlier text-based method was only able to identify participants with 97 per cent accuracy but effectively proved that it was possible to get accurate results without an inconveniently large number of electrodes being used to capture an EEG image, observing a "high degree of labelling accuracy achieved in all cases was achieved with the use of only 3 electrodes on the scalp". This is encouraging when it comes to the potential for developing EEG hardware designed specifically for use as part of a brainprint identification system.
Laszlo says that "it’s a big deal going from 97 to 100 percent because we imagine the applications for this technology being for high-security situations, like ensuring the person going into the Pentagon or the nuclear launch bay is the right person. You don’t want to be 97 percent accurate for that, you want to be 100 percent accurate."

Study co-author Zhanpeng Jin says that while the system is unlikely to be mass-produced for standard low-security applications, it has real potential for high-security scenarios: "We tend to see the applications of this system as being more along the lines of high-security physical locations, like the Pentagon or Air Force Labs, where there aren't that many users that are authorized to enter, and those users don't need to constantly be authorizing the way that a consumer might need to authorize into their phone or computer."