paper-with-me

홈 › Papers

Cactus Mechanisms: Optimal Differential Privacy Mechanisms in the Large-Composition Regime

2022-06-25 · Wael Alghamdi, Shahab Asoodeh, Flavio P. Calmon, Oliver Kosut, Lalitha Sankar, Fei Wei

Most differential privacy mechanisms are applied (i.e., composed) numerous times on sensitive data. We study the design of optimal differential privacy mechanisms in the limit of a large number of compositions. As a consequence of the law of large numbers, in this regime the best privacy mechanism is the one that minimizes the Kullback-Leibler divergence between the conditional output distributions of the mechanism given two different inputs. We formulate an optimization problem to minimize this divergence subject to a cost constraint on the noise. We first prove that additive mechanisms are optimal. Since the optimization problem is infinite dimensional, it cannot be solved directly; nevertheless, we quantize the problem to derive near-optimal additive mechanisms that we call "cactus mechanisms" due to their shape. We show that our quantization approach can be arbitrarily close to an optimal mechanism. Surprisingly, for quadratic cost, the Gaussian mechanism is strictly sub-optimal compared to this cactus mechanism. Finally, we provide numerical results which indicate that cactus mechanism outperforms the Gaussian mechanism for a finite number of compositions.

📄 PDF Abstract BibTeX arXiv:2207.00420

Code (0)

등록된 구현이 없습니다.

Tasks

Quantization

Similar Papers 제목 키워드 기반

Optimality of Staircase Mechanisms for Vector Queries under Differential Privacy

2026-01-21 · James Melbourne, Mario Diaz, Shahab Asoodeh arxiv

We study the optimal design of additive mechanisms for vector-valued queries under $ε$-differential privacy (DP). Given only the sensitivity of a query and a norm-monotone cost function measuring utility loss, we ask whi…

Privacy and Utility Tradeoff in Approximate Differential Privacy

2018-10-01 · Quan Geng, Wei Ding, Ruiqi Guo, Sanjiv Kumar

We characterize the minimum noise amplitude and power for noise-adding mechanisms in $(\epsilon, \delta)$-differential privacy for single real-valued query function. We derive new lower bounds using the duality of linear…

Near Instance-Optimality in Differential Privacy

2020-05-16 · Hilal Asi, John C. Duchi

We develop two notions of instance optimality in differential privacy, inspired by classical statistical theory: one by defining a local minimax risk and the other by considering unbiased mechanisms and analogizing the C…

regressionSensitivity

General Gaussian Noise Mechanisms and Their Optimality for Unbiased Mean Estimation

2023-01-31 · Aleksandar Nikolov, Haohua Tang

We investigate unbiased high-dimensional mean estimators in differential privacy. We consider differentially private mechanisms whose expected output equals the mean of the input dataset, for every dataset drawn from a f…

Privacy-Aware Randomized Quantization via Linear Programming

2024-06-01 · Zhongteng Cai, Xueru Zhang, Mohammad Mahdi Khalili

Differential privacy mechanisms such as the Gaussian or Laplace mechanism have been widely used in data analytics for preserving individual privacy. However, they are mostly designed for continuous outputs and are unsuit…

Quantization