You Xingyi, Zhao Xiaohu, Wang Yue, Sun Weiqing
National and Local Joint Engineering Laboratory of Internet Applied Technology on Mines, China University of Mining and Technology, Xuzhou 221008, China.
School of Information and Control Engineering, China University of Mining and Technology, Xuzhou 221008, China.
Entropy (Basel). 2024 May 31;26(6):479. doi: 10.3390/e26060479.
In light of growing concerns about the misuse of personal data resulting from the widespread use of artificial intelligence technology, it is necessary to implement robust privacy-protection methods. However, existing methods for protecting facial privacy suffer from issues such as poor visual quality, distortion and limited reusability. To tackle this challenge, we propose a novel approach called Diffusion Models for Face Privacy Protection (DIFP). Our method utilizes a face generator that is conditionally controlled and reality-guided to produce high-resolution encrypted faces that are photorealistic while preserving the naturalness and recoverability of the original facial information. We employ a two-stage training strategy to generate protected faces with guidance on identity and style, followed by an iterative technique for improving latent variables to enhance realism. Additionally, we introduce diffusion model denoising for identity recovery, which facilitates the removal of encryption and restoration of the original face when required. Experimental results demonstrate the effectiveness of our method in qualitative privacy protection, achieving high success rates in evading face-recognition tools and enabling near-perfect restoration of occluded faces.
鉴于人工智能技术的广泛应用引发了对个人数据滥用的日益担忧，实施强大的隐私保护方法很有必要。然而，现有的面部隐私保护方法存在视觉质量差、失真和可复用性有限等问题。为应对这一挑战，我们提出了一种名为“用于面部隐私保护的扩散模型”（DIFP）的新方法。我们的方法利用一个有条件控制且以现实为导向的面部生成器，来生成高分辨率的加密面部，这些面部具有照片般的真实感，同时保留原始面部信息的自然性和可恢复性。我们采用两阶段训练策略，在身份和风格的引导下生成受保护的面部，然后采用一种迭代技术来改进潜在变量以增强真实感。此外，我们引入了用于身份恢复的扩散模型去噪技术，以便在需要时便于去除加密并恢复原始面部。实验结果证明了我们的方法在定性隐私保护方面的有效性，在规避面部识别工具方面取得了高成功率，并能近乎完美地恢复被遮挡的面部。
