Your brain as a biometric marker

We haven't found that perfect combo of infallibility and convenience in a biometric-based security system. But research shows we are getting closer.

machine learning code brain matrix data
Credit: Shutterstock

You would think we have exhausted the range of biological markers that can serve as personal identification and provide access control. You would also think that with all the body parts scientists and the tech community have managed to incorporate into security, we would have found a hack-proof method by now.

You'd be wrong on all counts.

Over the years, voices, faces, blood, irises, and of course, fingerprints have been used to establish positive identification of an individual for various purposes. The business community, in particular, has been interested in such research because it could go a long way in solving the problem of IT-related theft. Already, there are biometric applications in which, say, an iris scan is used to identify an individual in order to give him or her access to data or a physical asset.

But these applications are still not completely foolproof, especially those that have been developed for widespread use. For example, Apple's iPhone 6 Touch ID was hacked days after it went on the market last year.

Could there be another biometric-based form of identification that might work?

Your brain as ID

Research coming out of the Basque Center on Cognition, Brain, and Language in Spain suggests that an individual's brainwaves could one day be used in a security solution.

Excerpts from the study's abstract (via Science Direct) describe the research:

The human brain continually generates electrical potentials representing neural communication. These potentials can be measured at the scalp, and constitute the electroencephalogram (EEG). When the EEG is time-locked to stimulation -- such as the presentation of a word -- and averaged over many such presentations, the Event-Related Potential (ERP) is obtained.

Translation: If you measure a person's brain signals responding to certain words, such as "cake" or "dog" or "privacy" you will find that the resulting signals are diverse enough to establish a definite identity.

The abstract continues:

We applied several pattern classifiers to ERPs representing the response of individuals to a stream of text designed to be idiosyncratically familiar to different individuals. Results indicate that there are robustly identifiable features of the ERP that enable labeling of ERPs as belonging to individuals with accuracy reliably above chance (in the range of 82–97%).

Translation: These signals are more accurate than rolling the dice.

The functional characteristics of components of the ERP are well understood, and some components represent processing that may differ uniquely from individual to individual -- such as the N400 component, which represents access to the semantic network.

Translation: This finding is different from similar experiments in which scientists have measured individual brain wave reactions to words or other stimuli. To give one example, researchers at the Oak Ridge National Laboratory have developed a method of identifying and authenticating individuals using brain wave data based on that person's thought process. However, the lead researcher for the Basque Center project, Dr. Blair C. Armstrong, believes that a technique based on semantic memory could be developed into a more personal, harder to compromise alternative, according to New Scientist.

Further, these features are stable over time, as indicated by continued accurate identification of individuals from ERPs after a lag of up to six months.

Translation: Dr. Armstrong's approach offers long-term reliability -- certainly, it should be better than a fingerprint scan that is required each and every time the data is accessed.

Even better, the high degree of labeling accuracy achieved in all cases was achieved with the use of only 3 electrodes on the scalp -- the minimal possible number that can acquire clean data.

Translation: Any solution based on this method will be very inconvenient if electrodes, no matter how many, are involved.

Starting Again

And with that it's back to the drawing board. Perhaps the team at the Basque Center can find a way to turn its research into a biometric-based security solution that is commercially viable and hopefully more accurate.

What the project does offer, though, is additional evidence that the research community is moving closer to this goal. If an answer doesn’t come from Dr. Armstrong's team then somebody else will hit on the winning combo of infallibility and convenience.

That, at least, is the unspoken assumption behind a market report by Tractica, which estimates that the value of the global biometrics market will grow to $14.9 billion by the year 2024, from its current value of $2 billion.

Such growth will be due to demand of course, but also supply -- in this case, supply of a viable biometric product.

This article is published as part of the IDG Contributor Network. Want to Join?

The march toward exascale computers
View Comments
Join the discussion
Be the first to comment on this article. Our Commenting Policies