A new watermarking scheme for diffusion models trains an autoencoder to embed and recover image watermarks through the generation process, but the reported robustness is undermined by flawed evaluation and an unjustified recovery step.
Digital watermarking and steganography
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
citation-role summary
background 1
citation-polarity summary
fields
eess.IV 1years
2025 1verdicts
REJECT 1roles
background 1polarities
background 1representative citing papers
citing papers explorer
-
Image Watermarking of Generative Diffusion Models
A new watermarking scheme for diffusion models trains an autoencoder to embed and recover image watermarks through the generation process, but the reported robustness is undermined by flawed evaluation and an unjustified recovery step.