Under identical differential privacy budgets, GANs show less membership inference leakage than diffusion models in the paper's MNIST experiments, a gap the authors attribute to training stability.
Title resolution pending
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.LG 1years
2025 1verdicts
REJECT 1representative citing papers
citing papers explorer
-
On the MIA Vulnerability Gap Between Private GANs and Diffusion Models
Under identical differential privacy budgets, GANs show less membership inference leakage than diffusion models in the paper's MNIST experiments, a gap the authors attribute to training stability.