International. Researchers at the Electronics and Telecommunications Research Institute (ETRI) in South Korea claim to have figured out how to accurately use bioacoustic body signatures to reveal identity, writes Digital Trends.
Published in the journal IEEE Transactions on Cybernetics, his research in experimental and next-generation biometrics argues that sound waves passing through the body can be used to identify a person with 97 percent accuracy because they analyze properties such as the individual's skin, tension in the joints, and bone density.
"We can think of our body as a musical instrument that has a unique shape and composition of materials," Joo Yong, one of the ETRI researchers on the project, told Digital Trends. "Our technology evaluates these features of our body by vibrating a certain part of the body, for example, a hand, and listening to the sound that propagates as we modify the frequency of arousal. Our system is sophisticated enough to extract the characteristics of our body as a proxy for a user's anatomical and biomaterial properties and differentiate the individual with great precision."
Biometric technology is susceptible to phishing attacks because it currently takes advantage of physiological features to create images for identification, however, things could be completely different if the vibration of the human body were used, the researchers say, because the unique spectral traits collected cannot be stolen, and could phase out counterfeiting to increase security. They found that bioacoustic spectral patterns don't undergo significant changes over time, but to ensure accuracy, the researchers are looking to add sensors to further integrate the technology with smartphones and wearable devices.
"In today's biometrics, such as fingerprint, iris and facial recognition, fake copies can be made for counterfeiting because they are based on the structural characteristics of the acquired image and therefore, once a template is stolen, it can be a permanent threat to counterfeiting," Yong said. Our method uses features within the body and extracts information in the frequency domain, which creates a new level of security and makes it useful for applications that require a high level of security."
