Does a Face Mask Protect my Privacy?: Deep Learning to Predict Protected Attributes from Masked Face Images

TL;DR

This study demonstrates that masked face images do not significantly reduce the ability of deep learning models to predict sensitive attributes like sex, race, and age, raising concerns about privacy even when masks are worn.

Contribution

The paper provides a novel analysis showing that privacy invasiveness persists with masked faces and introduces a CNN-based approach for evaluating privacy risks in biometric systems.

Findings

Accurately predicted sex (94.7%) from masked faces

Predicted race with 83.1% accuracy

Estimated age with MAE of 6.21 years

Abstract

Contactless and efficient systems are implemented rapidly to advocate preventive methods in the fight against the COVID-19 pandemic. Despite the positive benefits of such systems, there is potential for exploitation by invading user privacy. In this work, we analyse the privacy invasiveness of face biometric systems by predicting privacy-sensitive soft-biometrics using masked face images. We train and apply a CNN based on the ResNet-50 architecture with 20,003 synthetic masked images and measure the privacy invasiveness. Despite the popular belief of the privacy benefits of wearing a mask among people, we show that there is no significant difference to privacy invasiveness when a mask is worn. In our experiments we were able to accurately predict sex (94.7%),race (83.1%) and age (MAE 6.21 and RMSE 8.33) from masked face images. Our proposed approach can serve as a baseline utility to evaluate the privacy-invasiveness of artificial intelligence systems that make use of privacy-sensitive information. We open-source all contributions for re-producibility and broader use by the research community.