Differential Private Identification Protection for Face Images

In this chapter, we focus on providing theory guarantee to improve fundamental face de-identification. We propose IdentityDP, a face anonymization framework that combines a data-driven deep neural network (DNN) with a differential privacy (DP) mechanism. This framework encompasses three stages: facial representations disentanglement, \(\epsilon \) -IdentityDP perturbation and image reconstruction. Our model can effectively obfuscate the identity-related information of faces, preserve significant visual similarity, and generate high quality images that can be used for identity-agnostic computer vision tasks, such as detection, tracking, etc. Different from the previous methods, we can adjust the balance of privacy and utility through the privacy budget according to practical demands and provide a diversity of results without pre-annotations. Extensive experiments demonstrate the effectiveness and generalization ability of our proposed anonymization framework.