Respiratory-Based User Authentication and Device Pairing for at-Home OSA Test

Abstract

At-home screening systems for obstructive sleep apnea (OSA) can bring convenience to remote chronic disease management. However, the unsupervised home environment is subject to cheating from a non-compliant user, either by using another person to substitute for the test or manipulating the data communication during the test, which lowers the credibility of at-home OSA screening. To improve trustworthiness, this work presents SIENNA, an insider-resistant breathing-based authentication/pairing protocol. SIENNA leverages the uniqueness of breathing patterns to automatically authenticate a user and pairs two main components of an OSA kit, e.g., a mobile OSA app and a physiological monitoring radar system (PRMS). SIENNA does not require biometric enrollment and instead transforms the respiratory belt measurements taken during the user’s routine physical checkup into breathing biometrics comparable with the PRMS readings. Furthermore, it can operate within a noisy multi-target home environment and is secure against a co-located attacker through the usage of JADE-ICA, fuzzy commitment, and friendly jamming. We fully implemented SIENNA and evaluated its performance with medium-scale trials. Results show that SIENNA can achieve reliable ($>$ 90% success rate) user authentication and secure device pairing in a noisy environment against an attacker with full knowledge of the authorized user’s breathing biometrics.

Publication
IEEE TMC, submitted
Avatar
Yao Zheng
Associate Professor
Avatar
Yanjun Pan
Assistant Professor
Avatar
Marionne Millan
M.S., join Raytheon Technologies
Avatar
Samson Aggelopoulos
B.S., join Hawaiian Telcom
Avatar
Brian Lu
B.S., join Navfac Pacific
Avatar
Thomas Yang
B.S., join Nalu Scientific
Avatar
Stephanie Aelmore
B.S., Collaborator
Avatar
Willy Chang
B.S. OGS, M.S., join Microsoft Corporation