English

Local Distribution Obfuscation via Probability Coupling

Cryptography and Security 2023-07-19 v2 Databases Information Theory Machine Learning math.IT

Abstract

We introduce a general model for the local obfuscation of probability distributions by probabilistic perturbation, e.g., by adding differentially private noise, and investigate its theoretical properties. Specifically, we relax a notion of distribution privacy (DistP) by generalizing it to divergence, and propose local obfuscation mechanisms that provide divergence distribution privacy. To provide f-divergence distribution privacy, we prove that probabilistic perturbation noise should be added proportionally to the Earth mover's distance between the probability distributions that we want to make indistinguishable. Furthermore, we introduce a local obfuscation mechanism, which we call a coupling mechanism, that provides divergence distribution privacy while optimizing the utility of obfuscated data by using exact/approximate auxiliary information on the input distributions we want to protect.

Keywords

Cite

@article{arxiv.1907.05991,
  title  = {Local Distribution Obfuscation via Probability Coupling},
  author = {Yusuke Kawamoto and Takao Murakami},
  journal= {arXiv preprint arXiv:1907.05991},
  year   = {2023}
}

Comments

Full version of Allerton 2019 paper (This paper extends some part of the unpublished v3 of arXiv:1812.00939, while v4 of arXiv:1812.00939 extends the other part and is published in ESORICS'19.)

R2 v1 2026-06-23T10:20:05.489Z