Sniffing out your identity with breath biometrics

Sniff your identity with breath biometrics

Individual breath odor-based authentication using an artificial olfactory sensor could become possible in the near future, as depicted by this artist’s rendering. Credit: Kyushu University/Yanagida Lab

Biometric authentication such as fingerprint and iris scans are a staple of any spy movie, and trying to circumvent those security measures is often a key issue. But these days the technology is not limited to spies as fingerprint authentication and facial recognition are now common features on many of our phones.

Now, researchers have developed a new potential scent option for the biometric security toolkit: your breath. In a report published in Chemical communicationResearchers at Kyushu University’s Institute for Materials Chemistry and Engineering, in collaboration with the University of Tokyo, have developed an olfactory sensor that can identify individuals by analyzing the compounds in their breath.

Combined with machine learning, this “artificial nose”, built with a 16-channel sensor array, was able to authenticate up to 20 people with an average accuracy of more than 97%.

In this age of information and technology, biometric authentication is a critical way to protect valuable assets. From the usual suspects of fingerprints, palm prints, voices and faces to the less common options of ear acoustics and finger veins, there is a variety of biometrics that machines can use to identify you.

“These techniques depend on the physical uniqueness of each individual, but they are not foolproof. Physical features can be copied or even compromised by injury,” explains Chaiyanut Jirayupat, lead author of the study. “Lately, human scent has emerged as a new class of biometric authentication, essentially using your unique chemical makeup to authenticate who you are.”

Sniff your identity with breath biometrics

Image of an artificial olfactory sensor used for breath-based biometric authentication. The sensor is made of a 4×4 channel array for a total of 16 sensors. Each sensor detects a specific set of compounds found in the human breath. The data is then processed by a neural network, which then determines the individual. Credit: Kyushu University/Yanagida Lab

One such target is percutaneous gas — compounds produced by your skin. However, these methods have their limitations because the skin does not produce a high enough concentration of volatiles for machines to detect.

So the team turned to see if human breath could be used instead.

“The concentration of volatiles from the skin can be as high as a few parts per billion or trillions, while compounds exhaled through the breath can be as high as parts per million,” continues Jirayupat. “In fact, human breath has already been used to identify whether a person has cancer, diabetes and even COVID-19.”

The team began by analyzing subjects’ breath to see which connections could be used for biometric authentication. In total, 28 compounds were found to be viable options.

Based on this, they developed an olfactory sensor array with 16 channels, each of which could identify a specific set of connections. The sensor data was then passed to a machine learning system to analyze the composition of each person’s breath and develop a profile that can be used to distinguish an individual.

Sniff your identity with breath biometrics

The subjects start breathing in a collection bag. The bag is then connected to the olfactory sensor, which analyzes the compounds in the individual’s breath. Based on the concentration of the compounds, the machine learning system identifies the individual. Credit: Kyushu University/Yanagida lab

By testing the system with breath samples from six people, the researchers found that it could identify individuals with an average accuracy of 97.8%. This high level of accuracy remained consistent even when the sample size was increased to 20 subjects.

“This was a diverse group of individuals of different ages, genders and nationalities. It’s encouraging to see such high accuracy across the board,” explains Takeshi Yanagida, who led the study.

Nevertheless, he admits that more work is needed before it arrives on your next smartphone.

“In this work, our subjects had to fast for six hours before testing,” concludes Yanagida. “We have developed a good foundation. The next step will be to refine this technique to work regardless of diet. Fortunately, our current research has shown that adding more sensors and collecting more data can overcome this obstacle.”

‘E-nose’ smells mixtures of volatile organic compounds

More information:
Chaiyanut Jirayupat et al, Breath odor-based individual authentication by an artificial olfactory sensor system and machine learning, Chemical communication (2022). DOI: 10.1039/d1cc06384g

Provided by Kyushu University

Quote: Tracking Your Identity with Breath Biometrics (2022, June 22) retrieved June 22, 2022 from

This document is copyrighted. Other than fair dealing for personal study or research, nothing may be reproduced without written permission. The content is provided for informational purposes only.

Leave a Comment

Your email address will not be published.