Cyber security and authentication have been under attack in recent months, seemingly every other day. Just recently, more than 500 million passwords were stolen when Yahoo revealed its security was compromised.
The security risk suggests that a clever password is not enough to protect our personal information. Currently, fingerprint scans and iris identification are two types of authentication methods widely used.
However, fingerprints can be stolen and iris scans can be replicated. Maybe the only safe, unique method to protect our personal information is our brain.
In a recent study, researchers from Texas Tech University develop a method to use brain waves (EEG) to authenticate users with high accuracy.
They presented their findings recently to the Institute of Electrical and Electronics Engineers (IEEE) International Conference on Biometrics.
In the study, researchers recorded and analyzed brain waves in 25 formally diagnosed alcoholics and 25 non-alcoholic subjects.
The result showed that the lowest error rate obtained when identifying alcoholics was 25 percent, meaning a classification accuracy of approximately 75 percent.
Researchers suggest that brain waves can tell more about a person than just his or her identity. It could reveal medical, behavioral or emotional aspects of a person that, if brought to light, could be embarrassing or damaging to that person.
As EEG devices become much more affordable ($100), accurate and portable, and applications are designed to allow people to more readily read an EEG scan, the likelihood of that happening is dangerously high.
While the EEG is still being studied, the next wave of invention is already beginning. One of those technologies is functional near-infrared spectroscopy (fNIRS).
This technique has a much higher signal-to-noise ratio than an EEG. It gives a more accurate picture of brain activity given its ability to focus on a particular region of the brain.
For now, fNIRS technology is still quite expensive. However, it is possible that the prices will drop over time, potentially leading to a civilian application to this technology.
In the future, researchers will design device parameters to help recognize users very accurately while minimizing the amount of sensitive personal information being read.
News Source: Texas Tech University.
Figure legend: This Knowridge.com image is credited to National Institutes of Health (NIH).