SaTC: CORE: Small: Realizing Enhanced Authentication in the Mobile Era

Florida State University, Tallahassee FL

Investigators

Abstract

Mobile devices are an integral part of our lives, but can pose serious security and privacy threats, such unauthorized access to security-sensitive user data and services. This project explores human physiology to discover new biometrics of the human speech production system to enhance user authentication on mobile devices. These novel biometrics are captured and inferred using a variety of sensors that are present on mobile devices. The project also investigates the feasibility to deploy the discovered biometrics on mobile devices to improve security. The work leads to a new type of practically deployable biometric traits for mobile authentication. The outcomes of this project can be adopted by industry and could have a societal impact on facilitating a variety of security-sensitive mobile services and applications. The research activities are integrated into the Florida State University's Computer Science education program and include curriculum development, involvement of underrepresented minorities in computing, and K-12 educational outreach. This project explores the sensing capabilities of mobile devices to capture new biometrics of users for enhanced mobile authentication. The work innovates by targeting physiological and behavioral characteristics of the human speech production system, such as bone-conducted vibration and articulatory gestures, for mobile device user authentication. The project develops novel sensing techniques to capture the discovered biometrics, and systematically investigates the practicalities of implementing the novel biometrics on mobile devices in terms of hardware and context variability. Understanding the impact of device hardware and context variability helps strengthen the discovered biometric traits, by adapting them to drifts in contexts and behaviors. The discovered biometrics are evaluated and integrated with existing mobile authentication methods under a multimodal and multifactor authentication framework. The outcomes of this research can deepen our understanding of mobile devices authentication by considering human speech signals and the sensing capabilities of mobile devices. This award reflects NSF's statutory mission and has been deemed worthy of support through evaluation using the Foundation's intellectual merit and broader impacts review criteria.