Optimal Noise-Adding Mechanism in Additive Differential Privacy

Abstract

We derive the optimal $(0,\delta )$-differentially private query-output independent noise-adding mechanism for single real-valued query function under a general cost-minimization framework. Under a mild technical condition, we show that the optimal noise probability distribution is a uniform distribution with a probability mass at the origin. We explicitly derive the optimal noise distribution for general ${\ell }^p$ cost functions, including ${\ell }^1$ (for noise magnitude) and ${\ell }^2$ (for noise power) cost functions, and show that the probability concentration on the origin occurs when $\delta >\frac{p}{p+1}$. Our result demonstrates an improvement over the existing Gaussian mechanisms by a factor of two and three for $(0,\delta )$-differential privacy in the high privacy regime in the context of minimizing the noise magnitude and noise power, and the gain is more pronounced in the low privacy regime. Our result is consistent with the existing result for $(0,\delta )$-differential privacy in the discrete setting, and identifies a probability concentration phenomenon in the continuous setting.

arXiv comment10 pages, 5 figures. Accepted by the 22nd International Conference on Artificial Intelligence and Statistics (AISTATS 2019)

Cited by in corpus (5)

• AdaCliP: Adaptive Clipping for Private SGD
• On Mitigating the Utility-Loss in Differentially Private Learning: A new Perspective by a Geometrically Inspired Kernel Approach
• Learning Numeric Optimal Differentially Private Truncated Additive Mechanisms
• Efficient Privacy-Preserved Processing of Multimodal Data for Vehicular Traffic Analysis
• Differentially Private Link Prediction With Protected Connections