基于扩散模型的安全可逆面部匿名化
Secure and reversible face anonymization with diffusion models
AI总结：
本文提出基于扩散模型的安全可逆面部匿名化框架，通过秘密密钥条件实现匿名化与授权身份恢复，提升匿名化与去匿名化性能。
摘要：
面部匿名化旨在通过修改面部以保护敏感身份信息，同时保持视觉真实性和下游计算机视觉任务的实用性。当前方法难以同时确保高质量图像、强安全性保证以及受控的可逆性，以便在以后时间由授权方恢复身份。为了提高生成匿名面部的质量，近期方法采用了扩散模型。然而，这些新的基于扩散的匿名化方法没有提供限制去匿名化的机制，限制了其在现实中的应用。在本文中，我们提出了首个基于扩散模型的安全、可逆面部匿名化框架，通过秘密密钥条件进行。我们的方法将秘密密钥直接注入扩散过程，使匿名化和授权面部重建成为可能，同时防止未经授权的去匿名化。使用确定性的前向和反向扩散步骤保证了当正确秘密密钥可用时可以精确恢复身份。在CelebA-HQ和LFW上的实验表明，我们的方法在匿名化和去匿名化能力方面优于先前工作。我们还展示了我们的方法对错误或对抗性密钥去匿名化具有鲁棒性。我们的代码将公开发布。
英文摘要：
Face anonymization aims to protect sensitive identity information by altering faces while preserving visual realism and utility for downstream computer vision tasks. Current methods struggle to simultaneously ensure high image quality, strong security guarantees, and controlled reversibility for authorized identity recovery at a later time. To improve the image quality of generated anonymized faces, recent methods have adopted diffusion models. However, these new diffusion-based anonymization methods do not provide a mechanism to restrict de-anonymization to trusted parties, limiting their real-world applicability. In this paper, we present the first diffusion-based framework for secure, reversible face anonymization via secret-key conditioning. Our method injects the secret key directly into the diffusion process, enabling anonymization and authorized face reconstruction while preventing unauthorized de-anonymization. The use of deterministic forward and reverse diffusion steps guarantees exact identity recovery when the correct secret key is available. Experiments on CelebA-HQ and LFW demonstrate that our approach achieves better anonymization and de-anonymization capabilities than prior work. We also show that our method remains robust to incorrect or adversarial key de-anonymization. Our code will be made publicly available.
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。
