Does a Face Mask Protect my Privacy?: Deep Learning to Predict Protected Attributes from Masked Face Images
This work addresses privacy concerns for individuals using face recognition systems during the COVID-19 pandemic, but it is incremental as it applies an existing method to new data.
The paper tackles the problem of privacy invasion in face biometric systems by predicting sensitive attributes like sex, race, and age from masked face images, showing that masks do not significantly reduce privacy invasiveness with accuracies of 94.7% for sex and 83.1% for race, and an age prediction MAE of 6.21.
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.