MSGM is a score-adjustment unlearning method for score-based generative models that suppresses targeted content generation without full retraining.
Extracting training data from diffusion models
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
cs.LG 1years
2024 1verdicts
CONDITIONAL 1roles
background 1polarities
unclear 1representative citing papers
citing papers explorer
-
Moderating the Generalization of Score-based Generative Model
MSGM is a score-adjustment unlearning method for score-based generative models that suppresses targeted content generation without full retraining.