A normal approximation for joint frequency estimatation under Local Differential Privacy

@article{Carette2022ANA,
  title={A normal approximation for joint frequency estimatation under Local Differential Privacy},
  author={Thomas Carette},
  journal={ArXiv},
  year={2022},
  volume={abs/2205.11121}
}
  • T. Carette
  • Published 23 May 2022
  • Computer Science, Mathematics
  • ArXiv
In the recent years, Local Differential Privacy (LDP) has been one of the corner stone of privacy preserving data analysis. However, many challenges still opposes its widespread application. One of these problems is the scalability of LDP to high dimensional data, in particular for estimating joint-distributions. In this paper, we develop an approximate estimator for frequency joint-distribution estimation under so-called pure LDP protocols [1]. 

Figures from this paper

References

SHOWING 1-10 OF 18 REFERENCES
Marginal Release Under Local Differential Privacy
TLDR
The first tight theoretical bounds on the accuracy of marginals compiled under each approach are proved, which show that releasing information based on (local) Fourier transformations of the input is preferable to alternatives based directly on ( local) marginals.
Discrete Distribution Estimation under Local Privacy
TLDR
New mechanisms are presented, including hashed K-ary Randomized Response (KRR), that empirically meet or exceed the utility of existing mechanisms at all privacy levels and demonstrate the order-optimality of KRR and the existing RAPPOR mechanism at different privacy regimes.
Locally Differentially Private Heavy Hitter Identification
TLDR
In this paper, a proposed LDP protocol, which the authors call Prefix Extending Method (PEM), users are divided into groups, with each group reporting a prefix of her value and experiments show that under the same privacy guarantee and computational cost, PEM has better utility on both synthetic and real-world datasets than existing solutions.
A Comprehensive Survey on Local Differential Privacy
TLDR
This survey can serve as a good reference source for the research of LDP to deal with various privacy-related scenarios to be encountered in practice and identify future research directions and open challenges for LDP.
CALM: Consistent Adaptive Local Marginal for Marginal Release under Local Differential Privacy
TLDR
This paper considers the problem of constructing marginal tables given a set of user's multi-dimensional data while satisfying Local Differential Privacy (LDP), a privacy notion that protects individual user's privacy without relying on a trusted third party.
Building a RAPPOR with the Unknown: Privacy-Preserving Learning of Associations and Data Dictionaries
TLDR
This paper proposes a novel decoding algorithm for the RAPPOR mechanism that enables the estimation of “unknown unknowns,” i.e., strings the authors do not know they should be estimating, to enable learning without explicit dictionary knowledge.
Mutual Information Optimally Local Private Discrete Distribution Estimation
TLDR
This work proposes an efficient implementation of the $k$-subset mechanism for discrete distribution estimation, and shows its optimality guarantees over existing approaches.
Local Differential Privacy and Its Applications: A Comprehensive Survey
TLDR
This survey provides a comprehensive and structured overview of the local differential privacy technology and summarise and analyze state-of-the-art research in LDP and compare a range of methods in the context of answering a variety of queries and training different machine learning models.
Locally Differentially Private Protocols for Frequency Estimation
TLDR
This paper introduces a framework that generalizes several LDP protocols proposed in the literature and yields a simple and fast aggregation algorithm, whose accuracy can be precisely analyzed, resulting in two new protocols that provide better utility than protocols previously proposed.
Local, Private, Efficient Protocols for Succinct Histograms
TLDR
Efficient protocols and matching accuracy lower bounds for frequency estimation in the local model for differential privacy are given and it is shown that each user need only send 1 bit to the server in a model with public coins.
...
...