Fairness metrics computed on differentially private synthetic data differ from real-data values by up to 0.32 for some measures, despite staying below 0.1 on average, across Adult, COMPAS, and Diabetes.
Title resolution pending
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.CY 1years
2025 1verdicts
CONDITIONAL 1representative citing papers
citing papers explorer
-
Quantitative Auditing of AI Fairness with Differentially Private Synthetic Data
Fairness metrics computed on differentially private synthetic data differ from real-data values by up to 0.32 for some measures, despite staying below 0.1 on average, across Adult, COMPAS, and Diabetes.