The potential of realistic and useful synthetic data is significant. How...
In recent years, diffusion models have achieved tremendous success in th...
This work proposes Fed-GLOSS-DP, a novel approach to privacy-preserving
...
Differentially private data generation techniques have become a promisin...
As a long-term threat to the privacy of training data, membership infere...
Over the past six years, deep generative models have achieved a qualitat...
The wide-spread availability of rich data has fueled the growth of machi...
In recent years, the success of deep learning has carried over from
disc...