Research

This project develops privacy mechanisms for clinical video observation sessions, specifically focusing on mechanisms that protect the facial identity of the child under observation while retaining gaze and expression based information which is critical for diagnostic assessments.

This project investigated the effects of adding multiple loss terms to the optimization functions of a face swapping model.  We found that both an image reconstruction metric based on the eyes and a metric using difference in gaze angles derived by a pretrained expert model both increased the accuracy of gaze representation in generated faces.

This project proposes multiple privacy preserving techniques to protect users and user data in virtual reality.  We investigate both personal space and methods to preserve user privacy of recorded VR motion data to protect against re-identification attacks if a user's data is obtained my a malicous entity.