DP-DocLDM fine-tunes a latent diffusion model under differential privacy to generate synthetic document images, but the public pretraining set already contains the private benchmark datasets, invalidating the claimed privacy protection.
Proceedings of the International Conference on Document Analysis and Recognition, ICDAR1, 883–888 (2017)
1 Pith paper cite this work, alongside 115 external citations. Polarity classification is still indexing.
1
Pith paper citing it
115
external citations · OpenAlex
fields
cs.CR 1years
2025 1verdicts
REJECT 1representative citing papers
citing papers explorer
-
DP-DocLDM: Differentially Private Document Image Generation using Latent Diffusion Models
DP-DocLDM fine-tunes a latent diffusion model under differential privacy to generate synthetic document images, but the public pretraining set already contains the private benchmark datasets, invalidating the claimed privacy protection.