Researchers pitch voice recognition as two-factor authentication method for wearables
Researchers with the University of Alabama at Birmingham have developed a way to use speech signals received by wearables as part of a method of two-factor authentication, according to an announcement.
“Listening -Watch” was described in a paper published in the June by the Association for Computing Machinery Conference on Security and Privacy in Wireless and Mobile Networks. Professor Nitesh Sexena, Ph.D. and doctoral student Prakash Shrestha developed the system, in which speech embedded with a short random code is generated and played by a browser and received by a wearable device to enable secure authentication with minimal interaction by the user.
“Listening-Watch offers two key security features,” said Saxena, a professor in the UAB College of Arts and Sciences Department of Computer Science. “It uses random code encoded into speech to withstand remote attackers. Low-sensitivity microphones found in current wearable devices cannot capture distant sounds, which will thwart proximity attackers.”
An application on the wearable device would receive a push message prompting it to record the speech sounds played from the other device, and apply voice recognition technology to match the speech played by the browser and the speech received by the wearable.
Saxena is the director of the Security and Privacy In Emerging computer and networking Systems (SPIES) lab and the UAB CyberCorps Program, which is supported by the National Science Foundation.