分层反美学：保护面部隐私免受定制扩散模型侵害
Hierarchical Anti-Aesthetics: Protecting Facial Privacy against Customized Diffusion Models
AI总结：
提出分层反美学框架，通过全局和局部反美学奖励机制降低定制扩散模型的生成质量，从而保护面部隐私。
摘要：
定制扩散模型的兴起推动了个性化视觉内容创作的繁荣，但也引入了恶意滥用的严重风险，从而对个人隐私构成威胁。图像美学与人类对图像质量的感知密切相关。受此观察启发，我们从新颖的美学角度解决面部隐私保护问题，通过降低恶意定制模型的生成质量来减少面部身份泄露。具体来说，我们提出了一个分层反美学（HAA）框架，该框架在多个感知层面利用美学线索。HAA由两个关键分支组成：（1）全局反美学，通过构建全局反美学奖励机制和相应的损失来降低整体美学和生成质量；（2）局部反美学，通过使用局部反美学奖励机制和损失引导对抗性扰动作用于面部区域，从而破坏面部身份。通过整合两个分支，HAA在定制生成过程中实现了从全局到局部的反美学退化。大量实验表明，HAA在身份移除方面优于现有方法，为保护面部隐私提供了有效工具。
英文摘要：
The rise of customized diffusion models has fueled a boom in personalized visual content creation, but it also introduces serious risks of malicious misuse, thereby posing threats to personal privacy. Image aesthetics are strongly correlated with human perception of image quality. Motivated by this observation, we address facial privacy protection from a novel aesthetic perspective by degrading the generation quality of maliciously customized models, thus reducing facial identity leakage. Specifically, we propose a Hierarchical Anti-Aesthetics (HAA) framework that exploits aesthetic cues at multiple perceptual levels. HAA consists of two key branches: (1) Global Anti-Aesthetics, which degrades overall aesthetics and generation quality by constructing a global anti-aesthetic reward mechanism and a corresponding loss; and (2) Local Anti-Aesthetics, which disrupts facial identity by using a local anti-aesthetic reward mechanism and loss to guide adversarial perturbations toward facial regions. By integrating both branches, HAA achieves anti-aesthetic degradation from a global to a local level during customized generation. Extensive experiments show that HAA outperforms existing methods in identity removal, providing an effective tool for protecting facial privacy.
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。
