Optimal Conversion from Zero-Concentrated to Gaussian Differential Privacy
Abstract
Gaussian differential privacy (GDP) and zero-concentrated differential privacy (zCDP) are two competing privacy accounting frameworks, but they share similar minimax lower bounds in various estimation problems. Moreover, it is known that a mechanism satisfying $\mu$-GDP satisfies $(\mu^2/2)$-zCDP, whereas the converse fails to hold at the same calibration. In this paper, we establish the optimal reverse conversion, showing that every $\rho$-zCDP mechanism satisfies $\mu_{\mathrm{zCDP}}(\rho)$-GDP, where $\mu_{\mathrm{zCDP}}(\rho)=2\Phi^{-1}((1+e^{-t_\rho})^{-1})$ and $t_\rho$ uniquely solves the equation $\rho=t_\rho\tanh(t_\rho/2)$. We also obtain simplified bounds $\sqrt{\pi\rho}\leq\mu_{\mathrm{zCDP}}(\rho)\leq\sqrt{8\rho}$, with sharp constants, which imply equivalence of the two frameworks up to constants. This explains why their minimax risks agree up to a constant rescaling of the privacy budget. We show that the squared conversion is strictly convex, which implies that converting zCDP to GDP before applying composition or group privacy yields a tighter GDP guarantee than converting afterward. We also derive the sharp conversion from bounded-range and logistic DP mechanisms (e.g., exponential mechanism) to GDP, where converting before composition but after group privacy gives the tighter guarantee.