Scapegoat Generation for Privacy Protection from Deepfake

Authors: Gido Kato, Yoshihiro Fukuhara, Mariko Isogawa, Hideki Tsunashima, Hirokatsu Kataoka, Shigeo Morishima

Published: 2023-03-06 06:52:00+00:00

AI Summary

This paper proposes a novel deepfake prevention method called "scapegoat generation," which modifies an image to create a recognizable avatar while making it impossible to reconstruct the original face. This approach uses GAN inversion and optimization to generate a scapegoat image resistant to deepfake reconstruction, addressing limitations of previous detection and destruction methods.

Abstract

To protect privacy and prevent malicious use of deepfake, current studies propose methods that interfere with the generation process, such as detection and destruction approaches. However, these methods suffer from sub-optimal generalization performance to unseen models and add undesirable noise to the original image. To address these problems, we propose a new problem formulation for deepfake prevention: generating a ``scapegoat image'' by modifying the style of the original input in a way that is recognizable as an avatar by the user, but impossible to reconstruct the real face. Even in the case of malicious deepfake, the privacy of the users is still protected. To achieve this, we introduce an optimization-based editing method that utilizes GAN inversion to discourage deepfake models from generating similar scapegoats. We validate the effectiveness of our proposed method through quantitative and user studies.