Scapegoat Generation for Privacy Protection from Deepfake

TL;DR

This paper introduces a novel approach to deepfake prevention by generating a 'scapegoat image' that preserves user privacy and resists reconstruction, using GAN inversion and style modification.

Contribution

The paper proposes a new problem formulation and an optimization-based method for creating scapegoat images to protect privacy from deepfake models.

Findings

Effective in preventing deepfake reconstruction

Resistant to unseen deepfake models

Validated through quantitative and user studies

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.