Anti-Aesthetics: Protecting Facial Privacy against Customized Text-to-Image Synthesis
This addresses privacy and copyright risks from AI-generated content, offering a novel aesthetic-based approach, though it appears incremental as it builds on existing anti-aesthetic concepts.
The paper tackles the problem of protecting facial privacy against malicious misuse of customized text-to-image synthesis by proposing a Hierarchical Anti-Aesthetic (HAA) framework that degrades generation quality from global to local levels, with experiments showing it largely outperforms existing SOTA methods in identity removal.
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.