Search papers, labs, and topics across Lattice.
This paper introduces the Hierarchical Anti-Aesthetics (HAA) framework, which aims to protect facial privacy against the misuse of customized diffusion models by degrading the aesthetic quality of generated images. By employing a dual approach that includes both Global and Local Anti-Aesthetics, the framework effectively reduces facial identity leakage while maintaining a focus on image aesthetics. Experimental results demonstrate that HAA significantly outperforms existing methods in terms of identity removal, highlighting its potential as a robust privacy protection tool.
Degrading image aesthetics can be a powerful strategy to thwart identity leakage in personalized visual content generated by diffusion models.
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.
