Kristjan Greenewald

Kristjan Greenewald

Auto-generated profile, based on publicly available information

Kristjan Greenewald

IBM Watson AI Lab; IBM Research

Research Focus & Metrics

Academic Career Length

2Years (2025-Present)

(Calculated once Scilit publication data is synced: current year − year of first publication + 1)

Representative Publications

View All Publications
31 August 2025 in Journal of Privacy and Confidentiality
Verified
Journal Article
Open access
PDF file
CDCynthia Dwork
Cynthia Dwork
KGKristjan Greenewald
Kristjan Greenewald
MRManish Raghavan
Manish Raghavan
The US Decennial Census provides valuable data for both research and policy purposes. Census data are subject to a variety of disclosure avoidance techniques prior to release in order to preserve respondent confidentiality. While many are interested in studying the impacts of disclosure avoidance methods on downstream analyses, particularly with the introduction of differential privacy in the 2020 Decennial Census, these efforts are limited by a critical lack of data: The underlying "microdata," which serve as necessary input to disclosure avoidance methods, are kept confidential. In this work, we aim to address this limitation by providing tools to generate synthetic microdata solely from published Census statistics, which can then be used as input to any number of disclosure avoidance algorithms for the sake of evaluation and carrying out comparisons. We define a principled distributionover microdata given published Census statistics and design algorithms to sample from this distribution. We formulate synthetic data generation in this context as a knapsack-style combinatorial optimization problem and develop novel algorithms for this setting. While the problem we study is provably hard, weshow empirically that our methods work well in practice, and we offer theoretical arguments to explain our performance. Finally, we verify that the data we produce are "close" to the desired ground truth.