English

Privately Answering Counting Queries with Generalized Gaussian Mechanisms

Data Structures and Algorithms 2020-10-06 v1

Abstract

We consider the problem of answering kk counting (i.e. sensitivity-1) queries about a database with (ϵ,δ)(\epsilon, \delta)-differential privacy. We give a mechanism such that if the true answers to the queries are the vector dd, the mechanism outputs answers d~\tilde{d} with the \ell_\infty-error guarantee: E[d~d]=O(klogloglogklog(1/δ)ϵ).\mathcal{E}\left[||\tilde{d} - d||_\infty\right] = O\left(\frac{\sqrt{k \log \log \log k \log(1/\delta)}}{\epsilon}\right). This reduces the multiplicative gap between the best known upper and lower bounds on \ell_\infty-error from O(loglogk)O(\sqrt{\log \log k}) to O(logloglogk)O(\sqrt{\log \log \log k}). Our main technical contribution is an analysis of the family of mechanisms of the following form for answering counting queries: Sample xx from a \textit{Generalized Gaussian}, i.e. with probability proportional to exp((xp/σ)p)\exp(-(||x||_p/\sigma)^p), and output d~=d+x\tilde{d} = d + x. This family of mechanisms offers a tradeoff between 1\ell_1 and \ell_\infty-error guarantees and may be of independent interest. For p=O(loglogk)p = O(\log \log k), this mechanism already matches the previous best known \ell_\infty-error bound. We arrive at our main result by composing this mechanism for p=O(logloglogk)p = O(\log \log \log k) with the sparse vector mechanism, generalizing a technique of Steinke and Ullman.

Cite

@article{arxiv.2010.01457,
  title  = {Privately Answering Counting Queries with Generalized Gaussian Mechanisms},
  author = {Arun Ganesh and Jiazheng Zhao},
  journal= {arXiv preprint arXiv:2010.01457},
  year   = {2020}
}
R2 v1 2026-06-23T19:00:22.028Z