View source on GitHub |
Compute the stddev for the Gaussian mechanism with the given DP params.
tff.analytics.differential_privacy.analytic_gauss_stddev(
epsilon, delta, norm_bound, tol=1e-12
)
Calibrate a Gaussian perturbation for differential privacy using the analytic Gaussian mechanism of [Balle and Wang, ICML'18].
Reference: http://proceedings.mlr.press/v80/balle18a/balle18a.pdf
Returns | |
---|---|
sigma
|
Standard deviation of Gaussian noise needed to achieve (epsilon,delta)-DP under the given norm_bound. |