Privacy protection has become a top priority as the proliferation of AI techniques has led to widespread collection and misuse of personal data. Anonymization and visual identity information hiding are two important facial privacy protection tasks that aim to remove identification characteristics from facial images at the human perception level. However, they have a significant difference in that the former aims to prevent the machine from recognizing correctly, while the latter needs to ensure the accuracy of machine recognition. Therefore, it is difficult to train a model to complete these two tasks simultaneously. In this paper, we unify the task of anonymization and visual identity information hiding and propose a novel face privacy protection method based on diffusion models, dubbed Diff-Privacy. Specifically, we train our proposed multi-scale image inversion module (MSI) to obtain a set of SDM format conditional embeddings of the original image. Based on the conditional embeddings, we design corresponding embedding scheduling strategies and construct different energy functions during the denoising process to achieve anonymization and visual identity information hiding. Extensive experiments have been conducted to validate the effectiveness of our proposed framework in protecting facial privacy.

翻译：隐私保护已成为当务之急，因为人工智能技术的普及导致个人数据被广泛收集和滥用。匿名化和视觉身份信息隐藏是两项重要的面部隐私保护任务，旨在从人类感知层面移除面部图像中的身份特征。然而，二者存在显著差异：前者旨在防止机器正确识别，而后者需确保机器识别的准确性。因此，很难训练一个模型来同时完成这两项任务。本文统一了匿名化与视觉身份信息隐藏的任务，并提出一种基于扩散模型的新型面部隐私保护方法，命名为Diff-Privacy。具体而言，我们训练了所提出的多尺度图像反转模块（MSI），以获取原始图像的一组SDM格式条件嵌入。基于这些条件嵌入，我们设计了相应的嵌入调度策略，并在去噪过程中构建不同的能量函数，从而实现匿名化和视觉身份信息隐藏。大量实验验证了所提框架在保护面部隐私方面的有效性。