Practical Digital Disguises: Leveraging Face Swaps to Protect Patient Privacy

TL;DR

This paper introduces a novel face swapping pipeline for videos of children with autism, evaluating privacy and utility trade-offs, and highlighting limitations of current deep learning methods in real-world scenarios.

Contribution

It presents the first methodology to assess privacy-utility trade-offs in face swapping for patient privacy, focusing on autism assessment videos.

Findings

Face detection limits current face swapping in real-world videos.

Gaze and expression information are partially preserved by face swaps.

Face swapping outperforms blurring in utility preservation.

Abstract

With rapid advancements in image generation technology, face swapping for privacy protection has emerged as an active area of research. The ultimate benefit is improved access to video datasets, e.g. in healthcare settings. Recent literature has proposed deep network-based architectures to perform facial swaps and reported the associated reduction in facial recognition accuracy. However, there is not much reporting on how well these methods preserve the types of semantic information needed for the privatized videos to remain useful for their intended application. Our main contribution is a novel end-to-end face swapping pipeline for recorded videos of standardized assessments of autism symptoms in children. Through this design, we are the first to provide a methodology for assessing the privacy-utility trade-offs for the face swapping approach to patient privacy protection. Our methodology can show, for example, that current deep network based face swapping is bottle-necked by face detection in real world videos, and the extent to which gaze and expression information is preserved by face swaps relative to baseline privatization methods such as blurring.