paper-with-me

Papers

Optimal Unbiased Randomizers for Regression with Label Differential Privacy

2023-12-09 · NeurIPS 2023 11 · Ashwinkumar Badanidiyuru, Badih Ghazi, Pritish Kamath, Ravi Kumar, Ethan Leeman, Pasin Manurangsi, Avinash V Varadarajan, Chiyuan Zhang

We propose a new family of label randomizers for training regression models under the constraint of label differential privacy (DP). In particular, we leverage the trade-offs between bias and variance to construct better label randomizers depending on a privately estimated prior distribution over the labels. We demonstrate that these randomizers achieve state-of-the-art privacy-utility trade-offs on several datasets, highlighting the importance of reducing bias when training neural networks with label DP. We also provide theoretical results shedding light on the structural properties of the optimal unbiased randomizers.

📄 PDF Abstract BibTeX arXiv:2312.05659

Code (0)

등록된 구현이 없습니다.

Tasks

regression

Similar Papers 제목 키워드 기반

Optimal Algorithms for Mean Estimation under Local Differential Privacy

2022-05-05 · Hilal Asi, Vitaly Feldman, Kunal Talwar

We study the problem of mean estimation of $\ell_2$-bounded vectors under the constraint of local differential privacy. While the literature has a variety of algorithms that achieve the asymptotically optimal rates for t…

Optimal Compression of Locally Differentially Private Mechanisms

2021-10-29 · Abhin Shah, Wei-Ning Chen, Johannes Balle, Peter Kairouz 외

Compressing the output of \epsilon-locally differentially private (LDP) randomizers naively leads to suboptimal utility. In this work, we demonstrate the benefits of using schemes that jointly compress and privatize the …

RPWithPrior: Label Differential Privacy in Regression

2026-01-30 · Haixia Liu, Ruifan Huang arxiv

With the wide application of machine learning techniques in practice, privacy preservation has gained increasing attention. Protecting user privacy with minimal accuracy loss is a fundamental task in the data analysis an…

Stronger Privacy Amplification by Shuffling for Rényi and Approximate Differential Privacy

2022-08-09 · Vitaly Feldman, Audra McMillan, Kunal Talwar

The shuffle model of differential privacy has gained significant interest as an intermediate trust model between the standard local and central models [EFMRTT19; CSUZZ19]. A key result in this model is that randomly shuf…

Hiding Among the Clones: A Simple and Nearly Optimal Analysis of Privacy Amplification by Shuffling

2020-12-23 · Vitaly Feldman, Audra McMillan, Kunal Talwar

Recent work of Erlingsson, Feldman, Mironov, Raghunathan, Talwar, and Thakurta [EFMRTT19] demonstrates that random shuffling amplifies differential privacy guarantees of locally randomized data. Such amplification implie…