English

A Blessing of Dimensionality in Membership Inference through Regularization

Machine Learning 2023-04-17 v2 Machine Learning

Abstract

Is overparameterization a privacy liability? In this work, we study the effect that the number of parameters has on a classifier's vulnerability to membership inference attacks. We first demonstrate how the number of parameters of a model can induce a privacy--utility trade-off: increasing the number of parameters generally improves generalization performance at the expense of lower privacy. However, remarkably, we then show that if coupled with proper regularization, increasing the number of parameters of a model can actually simultaneously increase both its privacy and performance, thereby eliminating the privacy--utility trade-off. Theoretically, we demonstrate this curious phenomenon for logistic regression with ridge regularization in a bi-level feature ensemble setting. Pursuant to our theoretical exploration, we develop a novel leave-one-out analysis tool to precisely characterize the vulnerability of a linear classifier to the optimal membership inference attack. We empirically exhibit this "blessing of dimensionality" for neural networks on a variety of tasks using early stopping as the regularizer.

Keywords

Cite

@article{arxiv.2205.14055,
  title  = {A Blessing of Dimensionality in Membership Inference through Regularization},
  author = {Jasper Tan and Daniel LeJeune and Blake Mason and Hamid Javadi and Richard G. Baraniuk},
  journal= {arXiv preprint arXiv:2205.14055},
  year   = {2023}
}

Comments

26 pages, 14 figures

R2 v1 2026-06-24T11:31:06.173Z