English

Algorithms with More Granular Differential Privacy Guarantees

Cryptography and Security 2022-09-12 v1 Data Structures and Algorithms Machine Learning

Abstract

Differential privacy is often applied with a privacy parameter that is larger than the theory suggests is ideal; various informal justifications for tolerating large privacy parameters have been proposed. In this work, we consider partial differential privacy (DP), which allows quantifying the privacy guarantee on a per-attribute basis. In this framework, we study several basic data analysis and learning tasks, and design algorithms whose per-attribute privacy parameter is smaller that the best possible privacy parameter for the entire record of a person (i.e., all the attributes).

Keywords

Cite

@article{arxiv.2209.04053,
  title  = {Algorithms with More Granular Differential Privacy Guarantees},
  author = {Badih Ghazi and Ravi Kumar and Pasin Manurangsi and Thomas Steinke},
  journal= {arXiv preprint arXiv:2209.04053},
  year   = {2022}
}
R2 v1 2026-06-28T00:59:13.135Z