通过弱化扩散净化增强面部隐私保护
Enhancing Facial Privacy Protection via Weakening Diffusion Purification
AI总结：
针对扩散净化导致对抗人脸保护成功率低的问题，本文通过无条件嵌入引导对抗潜码修改并加入身份保持结构，在 CelebA-HQ 和 LADN 上提升了隐私保护的可迁移性与自然度。
摘要：
社交媒体的快速发展使得个人肖像图像被广泛分享，而自动人脸识别（AFR）系统具备大规模监控能力，因此这些图像带来了严重的隐私风险。因此，保护面部隐私以抵御未经授权的 AFR 系统至关重要。受新兴扩散模型生成能力的启发，近期方法采用扩散模型生成对抗性人脸图像以进行隐私保护。然而，这些方法受到扩散净化效应的影响，导致保护成功率（PSR）较低。本文首先提出学习无条件嵌入，以增强对抗性修改的学习能力，随后利用这些嵌入引导对抗性潜码的修改，从而弱化扩散净化效应。此外，我们整合了身份保持结构，以维持原始图像与生成图像之间的结构一致性，使人类观察者能够识别出生成图像与原始图像具有相同身份。在 CelebA-HQ 和 LADN 两个公共数据集上进行的大量实验证明了本文方法的优越性。与现有面部隐私保护方法生成的受保护人脸相比，本文方法生成的人脸在可迁移性和自然外观方面表现更优。
英文摘要：
The rapid growth of social media has led to the widespread sharing of individual portrait images, which pose serious privacy risks due to the capabilities of automatic face recognition (AFR) systems for mass surveillance. Hence, protecting facial privacy against unauthorized AFR systems is essential. Inspired by the generation capability of the emerging diffusion models, recent methods employ diffusion models to generate adversarial face images for privacy protection. However, they suffer from the diffusion purification effect, leading to a low protection success rate (PSR). In this paper, we first propose learning unconditional embeddings to increase the learning capacity for adversarial modifications and then use them to guide the modification of the adversarial latent code to weaken the diffusion purification effect. Moreover, we integrate an identity-preserving structure to maintain structural consistency between the original and generated images, allowing human observers to recognize the generated image as having the same identity as the original. Extensive experiments conducted on two public datasets, i.e., CelebA-HQ and LADN, demonstrate the superiority of our approach. The protected faces generated by our method outperform those produced by existing facial privacy protection approaches in terms of transferability and natural appearance.
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。
