DeepProtect：利用身份混合与属性失真的主动式换脸防御
DeepProtect: Proactive Face-Swapping Defense using Identity Blending and Attribute Distortion
在潜空间做通道级身份混合、并用文本提示导出的语义方向嵌入不可见对抗水印，可在不产生可见伪影的前提下破坏身份特征提取，为换脸防御与身份隐私保护提供可复用的扰动生成范式。
原文依据 applies semantic directions derived from user-provided text prompts to embed imperceptible adversarial watermarks
摘要译文
由模型翻译 · 术语统一 · 请对照原文核对关键结论换脸深度伪造能够实现逼真的身份迁移，这可用于创意目的，但也增加了身份被滥用的风险。主动式防御旨在通过阻碍从输入图像中提取身份特征来阻止深度伪造的生成，而身份特征提取正是身份驱动的换脸所必需的。现有的主动式防御方法试图通过阻碍准确的身份特征提取来保护人脸，但往往会引入可见伪影，且无法降低换脸深度伪造结果的视觉质量。本工作提出一种利用身份混合与属性失真的主动式换脸防御方法（DeepProtect），该方法在潜空间中融合全局身份，并结合局部提示驱动的对抗水印，以解决上述问题。本工作通过在潜空间中对多个身份进行通道级混合，并针对视觉一致性优化生成器，从而稀释显著的身份表征。所提出的方法在身份空间中失真面部组件，直接影响深度伪造中人脸的重建方式。该方法应用由用户提供的文本提示导出的语义方向，嵌入不可察觉的对抗水印，以选择性地失真面部属性，从而影响深度伪造结果的视觉保真度。所提出的方法在阻碍换脸深度伪造的同时保持了受保护图像的感知质量，为人脸隐私保护提供了一种稳健且实用的解决方案。实验结果表明，DeepProtect 在保持视觉一致性的同时，能够有效防御换脸深度伪造。
英文原文摘要 1625 字符
Face-swapping deepfakes allow realistic identity transfer, which can serve creative purposes but increases the risk of identity abuse. A proactive defense aims to prevent deepfake creation by obstructing identity feature extraction from input images, essential for identity-driven face-swapping. Existing proactive defense approaches aim to protect faces by hindering accurate identity feature extraction, but tend to introduce visible artifacts and fail to degrade the visual quality of the face-swapping deepfakes. This work proposes a proactive face-swapping defense using identity blending and attribute distortion (DeepProtect) that integrates global identity fusion in the latent space and local prompt-driven adversarial watermarking to address these problems. This work dilutes distinct identity representations by channel-wise blending of multiple identities in the latent space and optimizing the generator for visual consistency. The proposed approach distorts facial components in the identity space, directly influencing how faces are reconstructed in deepfakes. This approach applies semantic directions derived from user-provided text prompts to embed imperceptible adversarial watermarks that selectively distort facial attributes, affecting the visual fidelity of deepfake results. The proposed method hinders face-swapping deepfakes while preserving the perceptual quality of the protected images, offering a robust and practical solution for facial privacy protection. The experimental results reveal that DeepProtect effectively defends against face-swapping deepfakes while preserving visual consistency.