反美学：保护面部隐私免受定制文本到图像合成的影响
Anti-Aesthetics: Protecting Facial Privacy against Customized Text-to-Image Synthesis
AI总结：
针对定制扩散模型带来的面部隐私泄露风险，提出层次化反美学框架，通过全局与局部反美学机制降低生成质量，有效移除身份，优于现有方法。
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，但也带来了恶意滥用的风险，严重威胁到个人隐私和版权保护。一些研究表明，图像的美学属性与人类对图像质量的感知高度正相关。受此启发，我们从一个新颖且有趣的美学视角来处理该问题，以降低恶意定制模型的生成质量，从而更好地保护面部身份。具体而言，我们提出了一个层次化反美学（HAA）框架，以充分探索美学线索，该框架包含两个关键分支：1）全局反美学：通过建立全局反美学奖励机制和全局反美学损失，可以降低生成内容的整体美学质量；2）局部反美学：设计了局部反美学奖励机制和局部反美学损失，以引导对抗性扰动破坏局部面部身份。通过无缝整合这两个分支，我们的HAA在定制生成过程中有效地实现了从全局到局部的反美学目标。大量实验表明，HAA在身份移除方面大幅优于现有的最先进方法，为保护面部隐私和版权提供了有力工具。
英文摘要：
The rise of customized diffusion models has spurred a boom in personalized visual content creation, but also poses risks of malicious misuse, severely threatening personal privacy and copyright protection. Some studies show that the aesthetic properties of images are highly positively correlated with human perception of image quality. Inspired by this, we approach the problem from a novel and intriguing aesthetic perspective to degrade the generation quality of maliciously customized models, thereby achieving better protection of facial identity. Specifically, we propose a Hierarchical Anti-Aesthetic (HAA) framework to fully explore aesthetic cues, which consists of two key branches: 1) Global Anti-Aesthetics: By establishing a global anti-aesthetic reward mechanism and a global anti-aesthetic loss, it can degrade the overall aesthetics of the generated content; 2) Local Anti-Aesthetics: A local anti-aesthetic reward mechanism and a local anti-aesthetic loss are designed to guide adversarial perturbations to disrupt local facial identity. By seamlessly integrating both branches, our HAA effectively achieves the goal of anti-aesthetics from a global to a local level during customized generation. Extensive experiments show that HAA outperforms existing SOTA methods largely in identity removal, providing a powerful tool for protecting facial privacy and copyright.
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。
