CLIP2Protect：通过对抗性潜在搜索实现文本引导化妆的面部隐私保护
CLIP2Protect: Protecting Facial Privacy using Text-Guided Makeup via Adversarial Latent Search
AI总结：
针对人脸识别带来的隐私泄露问题，提出CLIP2Protect方法，通过生成模型潜在空间中的对抗性搜索结合文本引导化妆，生成自然且具有强黑盒迁移性的隐私保护人脸，在人脸验证任务上比现有最优方法绝对提升12.06%。
摘要：
基于深度学习的人脸识别系统的成功引发了严重的隐私担忧，因为它们能够在数字世界中实现对用户的未经授权追踪。现有的隐私增强方法无法生成既能保护面部隐私又不损害用户体验的自然图像。我们提出了一种新颖的两步面部隐私保护方法，该方法依赖于在预训练生成模型的低维流形中寻找对抗性潜在代码。第一步将给定的人脸图像反演到潜在空间中，并微调生成模型，以实现从潜在代码对给定图像的准确重建。这一步提供了良好的初始化，有助于生成与给定身份相似的高质量人脸。随后，使用用户定义的化妆文本提示和身份保持正则化来引导潜在空间中的对抗性代码搜索。大量实验表明，我们方法生成的人脸具有更强的黑盒可迁移性，在人脸验证任务下，与最先进的面部隐私保护方法相比，绝对增益为12.06%。最后，我们展示了所提方法在商业人脸识别系统中的有效性。我们的代码可在 https://github.com/fahadshamshad/Clip2Protect 获取。
英文摘要：
The success of deep learning based face recognition systems has given rise to serious privacy concerns due to their ability to enable unauthorized tracking of users in the digital world. Existing methods for enhancing privacy fail to generate naturalistic images that can protect facial privacy without compromising user experience. We propose a novel two-step approach for facial privacy protection that relies on finding adversarial latent codes in the low-dimensional manifold of a pretrained generative model. The first step inverts the given face image into the latent space and finetunes the generative model to achieve an accurate reconstruction of the given image from its latent code. This step produces a good initialization, aiding the generation of high-quality faces that resemble the given identity. Subsequently, user-defined makeup text prompts and identity-preserving regularization are used to guide the search for adversarial codes in the latent space. Extensive experiments demonstrate that faces generated by our approach have stronger black-box transferability with an absolute gain of 12.06% over the state-of-the-art facial privacy protection approach under the face verification task. Finally, we demonstrate the effectiveness of the proposed approach for commercial face recognition systems. Our code is available at https://github.com/fahadshamshad/Clip2Protect.
机构、总结、中文摘要均由AI分析而来，可能存在错误，请以论文正文为准。
