ABSTRACT
Undoubtedly COVID-19 is one of the most disruptive pandemics in recent history, adversely affecting individuals, societies, and economies through severe limitations imposed on activities involving gatherings and travel. Among many tools envisioned in battling such pandemics are immunity passports allowing vaccinated or immune individuals to bypass the restrictive measures. However, this proposal also raises many security, privacy, and ethical issues. Due to the sensitive medical records, companies and recreation centres do not have direct access to the COIVD vaccine database;on the other hand, the vaccine results are easily forgeable. One solution is public access to the vaccination database, which is not acceptable for privacy reasons. Our solution securely combines the vaccination results with the user's biometric authentication result to generate a binary result, such that 0 means this person either not authenticated or not vaccinated, and 1 means this person is vaccinated and authenticated so he/she may use an intended service. Our scheme is based on Secure MultiParty Computations (MPC) and preserves both the privacy of the biometric query and the database. At the same time, it also prevents the inquiring service provider from learning about the vaccination result. © 2021 IEEE.
ABSTRACT
Ocular biometrics is attracting exceeding attention from research community and industry alike thanks to its accuracy, security, and ease of use in mobile devices, especially in the presence of occlusions such as masks worn during the COVID-19 pandemic. When considering the extended periocular region, eyebrows have not been getting enough attention due to their perceived low uniqueness. In this paper, we evaluate a mobile-friendly deep-learning model for eyebrow-based user authentication. Specifically, we used a fine-tuned lightCNN model for eyebrow based user authentication with promising results on a particularly challenging dataset and evaluation protocol (open-set with simulated twins). The methods achieved 0.99 AUC and 4.3% EER in VISOB dataset and 0.98 AUC and 5.6% EER on SiW datasets using closed-set and open-set analysis, respectively. © 2020 German Computer Association (Gesellschaft für Informatik e.V.).