CISPA
Browse

Have it your way: Individualized Privacy Assignment for DP-SGD

Download (2.81 MB)
preprint
posted on 2024-02-19, 09:36 authored by Franziska Boenisch, Christopher Mühl, Adam Dziedzic, Roy Rinberg, Nicolas Papernot
When training a machine learning model with differential privacy, one sets a privacy budget. This budget represents a maximal privacy violation that any user is willing to face by contributing their data to the training set. We argue that this approach is limited because different users may have different privacy expectations. Thus, setting a uniform privacy budget across all points may be overly conservative for some users or, conversely, not sufficiently protective for others. In this paper, we capture these preferences through individualized privacy budgets. To demonstrate their practicality, we introduce a variant of Differentially Private Stochastic Gradient Descent (DP-SGD) which supports such individualized budgets. DP-SGD is the canonical approach to training models with differential privacy. We modify its data sampling and gradient noising mechanisms to arrive at our approach, which we call Individualized DP-SGD (IDP-SGD). Because IDP-SGD provides privacy guarantees tailored to the preferences of individual users and their data points, we find it empirically improves privacy-utility trade-offs.

History

Primary Research Area

  • Trustworthy Information Processing

Journal

CoRR

Volume

abs/2303.17046

Sub Type

  • Article

BibTeX

@article{Boenisch:Mühl:Dziedzic:Rinberg:Papernot:2023, title = "Have it your way: Individualized Privacy Assignment for DP-SGD", author = "Boenisch, Franziska" AND "Mühl, Christopher" AND "Dziedzic, Adam" AND "Rinberg, Roy" AND "Papernot, Nicolas", year = 2023, month = 3, journal = "CoRR" }

Usage metrics

    Categories

    No categories selected

    Licence

    Exports

    RefWorks
    BibTeX
    Ref. manager
    Endnote
    DataCite
    NLM
    DC