Search Results for author:
Found 3 papers, 0 papers with code
Stable Signature is Unstable: Removing Image Watermark from Diffusion Models
Our results show that our attack can effectively remove the watermark from a diffusion model such that its generated images are non-watermarked, while maintaining the visual quality of the generated images.
Watermark-based Detection and Attribution of AI-Generated Content
Several companies--such as Google, Microsoft, and OpenAI--have deployed techniques to watermark AI-generated content to enable proactive detection.
A Transfer Attack to Image Watermarks
The robustness of such watermark-based detector against evasion attacks in the white-box and black-box settings is well understood in the literature.
Cannot find the paper you are looking for? You can
Submit a new open access paper.
