Differential privacy and swapping: Examining de-identification's impact on minority representation and privacy preservation in the US census

M Christ, S Radway, SM Bellovin - 2022 IEEE symposium on …, 2022 - ieeexplore.ieee.org
There has been considerable controversy regarding the accuracy and privacy of de-
identification mechanisms used in the US Decennial Census. We theoretically and …

Between privacy and utility: On differential privacy in theory and practice

J Seeman, D Susser - ACM Journal on Responsible Computing, 2024 - dl.acm.org
Differential privacy (DP) aims to confer data processing systems with inherent privacy
guarantees, offering strong protections for personal data. But DP's approach to privacy …

Does Label Differential Privacy Prevent Label Inference Attacks?

R Wu, JP Zhou, KQ Weinberger, C Guo - arXiv preprint arXiv:2202.12968, 2022 - arxiv.org
Label differential privacy (label-DP) is a popular framework for training private ML models on
datasets with public features and sensitive private labels. Despite its rigorous privacy …

Differential perspectives: Epistemic disconnects surrounding the US Census Bureau's use of differential privacy

D Boyd, J Sarathy - Harvard Data Science Review (Forthcoming), 2022 - papers.ssrn.com
Abstract When the US Census Bureau announced its intention to modernize its disclosure
avoidance procedures for the 2020 Census, it sparked a controversy that is still underway …

[PDF][PDF] A linear reconstruction approach for attribute inference attacks against synthetic data

MSMS Annamalai, A Gadotti, L Rocher - 2024 - usenix.org
Recent advances in synthetic data generation (SDG) have been hailed as a solution to the
difficult problem of sharing sensitive data while protecting privacy. SDG aims to learn …

Comment: The essential role of policy evaluation for the 2020 census disclosure avoidance system

CT Kenny, S Kuriwaki, C McCartan… - arXiv preprint arXiv …, 2022 - arxiv.org
In" Differential Perspectives: Epistemic Disconnects Surrounding the US Census Bureau's
Use of Differential Privacy," boyd and Sarathy argue that empirical evaluations of the …

Synthetic Health Data: Real Ethical Promise and Peril

D Susser, DS Schiff, S Gerke, LY Cabrera… - Hastings Center …, 2024 - Wiley Online Library
Researchers and practitioners are increasingly using machine‐generated synthetic data as
a tool for advancing health science and practice, by expanding access to health data while …

Advancing differential privacy: Where we are now and future directions for real-world deployment

R Cummings, D Desfontaines, D Evans… - arXiv preprint arXiv …, 2023 - arxiv.org
In this article, we present a detailed review of current practices and state-of-the-art
methodologies in the field of differential privacy (DP), with a focus of advancing DP's …

Estimating racial disparities when race is not observed

C McCartan, R Fisher, J Goldin, DE Ho, K Imai - 2024 - nber.org
The estimation of racial disparities in various fields is often hampered by the lack of
individuallevel racial information. In many cases, the law prohibits the collection of such …

Provable membership inference privacy

Z Izzo, J Yoon, SO Arik, J Zou - arXiv preprint arXiv:2211.06582, 2022 - arxiv.org
In applications involving sensitive data, such as finance and healthcare, the necessity for
preserving data privacy can be a significant barrier to machine learning model development …