May 14, 2024, 4:47 a.m. | Yuepeng Hu, Zhengyuan Jiang, Moyang Guo, Neil Gong

cs.CV updates on arXiv.org arxiv.org

arXiv:2405.07145v1 Announce Type: cross
Abstract: Watermark has been widely deployed by industry to detect AI-generated images. A recent watermarking framework called \emph{Stable Signature} (proposed by Meta) roots watermark into the parameters of a diffusion model's decoder such that its generated images are inherently watermarked. Stable Signature makes it possible to watermark images generated by \emph{open-source} diffusion models and was claimed to be robust against removal attacks. In this work, we propose a new attack to remove the watermark from a …

abstract ai-generated images arxiv cs.cr cs.cv decoder diffusion diffusion model diffusion models framework generated image images industry meta parameters type watermark watermarking

Software Engineer for AI Training Data (School Specific)

@ G2i Inc | Remote

Software Engineer for AI Training Data (Python)

@ G2i Inc | Remote

Software Engineer for AI Training Data (Tier 2)

@ G2i Inc | Remote

Data Engineer

@ Lemon.io | Remote: Europe, LATAM, Canada, UK, Asia, Oceania

Artificial Intelligence – Bioinformatic Expert

@ University of Texas Medical Branch | Galveston, TX

Lead Developer (AI)

@ Cere Network | San Francisco, US