Do you like pizza? Would you consider yourself a boat enthusiast, a landlubber or none of the above? Does comedian Adam Sandler make you laugh or make you cringe?
Your responses to certain stimuli — foods, celebrities, words, seafaring vessels, you name it — might seem trivial, but they say a lot about you. In fact (with the proper clearance), these responses could gain you access into restricted areas of the Pentagon.
A new technology developed at Binghamton University can identify you simply by measuring your brain’s response to different stimuli. The technology has garnered attention from media outlets around the world, including National Geographic, which spent a day interviewing and filming on campus. It’s called brainprint, and it could revolutionize the security industry.
A team of researchers, led by Assistant Professor of Psychology Sarah Laszlo and Assistant Professor of Electrical and Computer Engineering Zhanpeng Jin, recorded the brain activity of people wearing an electroencephalogram headset while they looked at a series of 500 images designed specifically to elicit unique responses from person to person — e.g., a slice of pizza, a boat, Anne Hathaway, the word “conundrum.” Each image flashed on a monitor for only half a second.
In their original study, titled “Brainprint,” published in May on the website of the academic journal Neurocomputing, the research team was able to identify one person out of a group of 32 by that person’s responses, with 97 percent accuracy. More recently, they were 100 percent accurate at identifying one person out of a group of 30.
“When you take hundreds of these images, where every person is going to feel differently 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,” Laszlo says.
For example, stimuli used in the experiment included images of sushi. Laszlo picked sushi because it’s a divisive food. Some love it. Some hate it because it’s slimy. Some have never tried it and don’t know what to think about it.
It’s these specific responses that set people apart, and Brainprint exploits that.
If you’ve ever used a fingerprint scanner to access a gym or your smartphone, you’ve used a biometric system.
The idea of using brain activity as a biometric had been proposed before, but most of these approaches focused on active thinking. For example, you would think of a car, your brain activity would be recorded, and you would access the system again by thinking of the same car. Brainprint is different.
“The key idea is that we want to identify and recognize the individual person based on their inside thinking. Inside-brain activity is not visible to anyone else,” Jin says. “Even more exciting is that we want to use a nonvolitional response. That means even the user cannot be aware of it.”
Laszlo and Jin want to establish a new biometric, one that can’t be compromised. It’s gruesome to think about, but someone could easily cut off your finger and use your fingerprint to impersonate you.
Brain biometrics are appealing because they can be canceled, and they cannot be stolen by malicious means the way a finger or retina can. You can’t cut off somebody’s brain like you could a finger — the brain would be rendered useless.
“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,” Laszlo says. “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’ his brainprint.”
If a criminal tried to force someone, at gunpoint, to use his or her brainprint, the person wouldn’t have the capability to do so.
“We think that you can’t even threaten somebody and have their brainprint still work, because if you threaten someone, say with violence, that makes them stressed out,” Jin says. “When you are stressed, your brain activity changes quite dramatically. We think that stress would prevent the person from being able to use his brainprint to authenticate the system.”
While engineers have been responsible for most attempts at brain biometrics, brainprint is the result of a unique collaboration between an engineer [Jin] and a psychologist [Laszlo].
“That collaboration has been really fruitful,” Laszlo says. “It crosses cybersecurity and biometrics and cognitive neuroscience and psychology, and I think it’s why our brainprint protocol is more accurate and faster than any of the existing protocols.”
Coming from the perspective of a psychologist, she is most interested in brainprint for what it reveals about the human brain.
“For me, as a cognitive scientist, what I’ve learned the most from doing this is it’s something that we all sort of think must be true — that our brains and our thoughts are unique — but hasn’t really been demonstrated with hard data. I think that’s what this project demonstrates — that we’re unique, our brains are unique, our thoughts are unique and our feelings are unique. And that’s not just some hand-wavy, ‘you’re a speckled snowflake’ sort of thing to say. It’s really quantifiable; you are not the same as any other person.”
Don’t expect to access your smartphone with your mind anytime soon. Laszlo and Jin don’t see brainprint as the kind of system that would be mass-produced for low-security applications (at least not in the near future), but it could be used at checkpoints to high-security locations like the Pentagon, naval research bases and nuclear instrumentation labs.
“The expense of the equipment and the amount of time that it takes to collect a brainprint is, at least now, much too long for someone to want to use it to get into an iPhone or get into a computer, because you don’t want to spend two minutes recording brain activity every time you want to look at your phone,” Jin says. Once the brainprint of a person is established, it takes several minutes to collect a fresh brainprint in order to verify the identity of that person.
“This is for places where there aren’t many people who are allowed in, and where it’s important and worth the two minutes to see if the person really is who he says he is,” Jin adds.
While wearable EEG headsets are easier to use and more comfortable than research-level headsets, there are some difficulties. They’re still not as comfortable as touching your finger to glass, for example, but Jin imagines the technology becoming more cost-effective and user-friendly in the future.
For the time being, he and Laszlo are happy for what they have accomplished.
“Both of us are very excited about this research idea, and we provide complementary expertise,” Jin says. “That’s a perfect example of transdisciplinary research carried out successfully.”
“A lot of my research is very dry and not very interesting to other people outside of my lab,” Laszlo says. “But this — even if I call my mom and I tell her about this, she gets all excited. I get all excited. My graduate students and I, we’re jumping up and down, we’re laughing. The ideas are coming so fast, and everyone we tell about it is so interested in it. I love working on this project.”