Authentication solutions for personal computing devices, such as people use to login to their laptops and smart phones, are usually designed with able-bodied individuals in mind. But designs for the able-bodied often make authentication difficult for people with disabilities, particularly for those with upper extremity impairment. Such persons often lack the range of motion, strength, endurance, speed, and/or accuracy associated with normal behavior of the arms, hands, or fingers. Over 20 million people in the U.S. alone suffer from conditions that lead to upper extremity impairment. This project aims to develop a suite of authentication solutions for people with these impairments. The research will aim for authentication solutions that these individuals can use effectively to securely access their devices. The outcome of this project will be innovations in authentication that can be readily adopted by commercial technology providers to beneficially impact people with upper extremity impairments.
This project will involve the development of a combined group of several authentication solutions that people with upper extremity impairment often use. These include involuntary head-motion-based physiological responses, blinking patterns, and pressure patterns. The research examines strategies that reduce authentication errors when using these behaviors, particularly those emanating from the non-permanence of such behaviors, using a family of authentication models and through periodic model re-training. A robust test-bed designed for the project will enable rapid plug-and-play evaluation of authentication solutions. The testing and validation framework will include red-team challenges to allow for expansive security evaluation of the authentication solutions developed. New techniques developed in this project will be integrated into undergraduate and graduate education. A hackathon will be used to raise public awareness about the importance of cybersecurity solutions targeted at people with disabilities.
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.
|