Practical Digital Disguises: Leveraging Face Swaps to Protect Patient Privacy
This work addresses privacy protection in healthcare video data, specifically for autism research, but is incremental as it builds on existing face swapping techniques.
The paper tackles the problem of preserving patient privacy in video datasets by developing a novel end-to-end face swapping pipeline for autism symptom assessments in children, showing that current methods are bottlenecked by face detection and quantifying preservation of gaze and expression information compared to blurring.
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.