For linear regression with output perturbation, releasing synthetic points generated from hidden random inputs amplifies differential privacy by roughly the inverse input dimension, unless the adversary controls the seed.
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
CONDITIONAL 1representative citing papers
citing papers explorer
-
Privacy Amplification Through Synthetic Data: Insights from Linear Regression
For linear regression with output perturbation, releasing synthetic points generated from hidden random inputs amplifies differential privacy by roughly the inverse input dimension, unless the adversary controls the seed.