RPSG generates realistic synthetic replicas of private text by combining private seeds with public LLMs and a formal differential privacy mechanism in candidate selection.
Title resolution pending
2 Pith papers cite this work. Polarity classification is still indexing.
2
Pith papers citing it
representative citing papers
DP-GRAPE reduces memory in differentially private neural network training by using random Gaussian projections on gradients instead of SVD, achieving comparable privacy-utility tradeoffs to DP-SGD and scaling to 6.7B parameter models.
citing papers explorer
-
Private Seeds, Public LLMs: Realistic and Privacy-Preserving Synthetic Data Generation
RPSG generates realistic synthetic replicas of private text by combining private seeds with public LLMs and a formal differential privacy mechanism in candidate selection.
-
Memory-Efficient Differentially Private Training with Gradient Random Projection
DP-GRAPE reduces memory in differentially private neural network training by using random Gaussian projections on gradients instead of SVD, achieving comparable privacy-utility tradeoffs to DP-SGD and scaling to 6.7B parameter models.