4 papers
Geometry-Aware Tabular Diffusion
David Turtora Zagardo
Tabular synthesis is critical for privacy-preserving sharing and augmentation, yet diffusion models rely on implicit mechanisms to capture inter-column relationships. We introduce…
FERRET: Private Deep Learning Faster And Better Than DPSGD
David Zagardo
We revisit 1-bit gradient compression through the lens of mutual-information differential privacy (MI-DP). Building on signSGD, we propose FERRET--Fast and Effective Restricted Rel…
Differentially Private Block-wise Gradient Shuffle for Deep Learning
David Zagardo
Traditional Differentially Private Stochastic Gradient Descent (DP-SGD) introduces statistical noise on top of gradients drawn from a Gaussian distribution to ensure privacy. This…
Too Good to be True? Turn Any Model Differentially Private With DP-Weights
David Zagardo
Imagine training a machine learning model with Differentially Private Stochastic Gradient Descent (DP-SGD), only to discover post-training that the noise level was either too high,…