Improving the Gaussian Mechanism for Differential Privacy: Analytical Calibration and Optimal Denoising

@inproceedings{Balle2018ImprovingTG,
  title={Improving the Gaussian Mechanism for Differential Privacy: Analytical Calibration and Optimal Denoising},
  author={Borja Balle and Yu-Xiang Wang},
  booktitle={ICML},
  year={2018}
}
The Gaussian mechanism is an essential building block used in multitude of differentially private data analysis algorithms. In this paper we revisit the Gaussian mechanism and show that the original analysis has several important limitations. Our analysis reveals that the variance formula for the original mechanism is far from tight in the high privacy regime (ε → 0) and it cannot be extended to the low privacy regime (ε → ∞). We address these limitations by developing an optimal Gaussian… CONTINUE READING
Tweets
This paper has been referenced on Twitter 19 times. VIEW TWEETS