Original news release was published by the University of Saarland.
User privacy and data security is a long-standing issue with everything connected, and even more so now that we carry and wear more data-sponges than we ever did. PIN codes and passwords are still the go-to way of securing one’s information, but it is safe to say that biometric identifiers, such as fingerprint, voice, and iris scanners have already made it into the mainstream. This list is about to grow, as computer scientists from the University of Saarland and the University of Stuttgart have developed a biometric identifier for Google Glass eyewear computer, that uses the skull to verify the user identity.
“Eyewear computers such as Google Glass are already being used in companies and universities, for helping with physics experiments and in chemistry labs, documenting medical examinations and assisting pediatricians during operations,” says Andreas Bulling from the Cluster of Excellence on “Multimodal Computing and Interaction” at Saarland University. “Not only may the users have no hands free to enter a password, they often share a Google Glass among each other and save sensitive data on the device,” explains Bulling.
To protect the eyewear computer and its data in case of theft, and to identify legitimate users and prove their authenticity, the researchers have developed a method which uses components the Google Glass already has. Besides the miniature microphone, they use the so-called bone conduction speaker, which is barely visible and is embedded in the frame near the right ear. Using bone conduction, it transmits sounds to the ear in the same way as special hearing aids do. It directs sound vibrations through the surrounding skull bone directly to the inner ear.
“Because the skull is individual, the sound signal is changed in a way which is unique for every person. Hence, we can use it as a biometric identifier,” Bulling explains.
“SkullConduct“, as they have dubbed their indentification system is using the Google Glass’ built-in microphone to record the signal returning from the skull at a unique frequency. It is then possible to compose the identifying features into a digital imprint used for repeated authentication.
Bulling and his colleagues have tested SkullConduct on ten people with 97% accuracy in a controlled environment with no backgrond noise. As they carry on with their research, they will be putting their system to the test in everyday life, while experimenting with ultrasound’s range, which would be inaudible by the user during the authentication process. They also plan on improving the modularity of the design, which would enable SkullConduct to be used with other devices, like smartphones, as opposed to just eyewear.
