CAT trains lightweight adapters on the latent autoencoder to realign representations of protected images, reducing the effectiveness of nine protective perturbation methods on Stable Diffusion customization.
Extracting Training Data from Diffusion Models
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.CV 1years
2025 1verdicts
CONDITIONAL 1representative citing papers
citing papers explorer
-
CAT: Contrastive Adversarial Training for Evaluating the Robustness of Protective Perturbations in Latent Diffusion Models
CAT trains lightweight adapters on the latent autoencoder to realign representations of protected images, reducing the effectiveness of nine protective perturbation methods on Stable Diffusion customization.