Diverse Community Data for Benchmarking Data Privacy Algorithms

TL;DR

This paper presents a NIST benchmarking program that provides diverse community data, evaluation tools, and analysis to improve understanding and fairness of data privacy algorithms for tabular data.

Contribution

It introduces a comprehensive benchmarking framework with diverse datasets, evaluation metrics, and open source tools to advance deidentification technology and address bias issues.

Findings

Evaluation results demonstrate the effectiveness of the benchmarking tools.

Diverse datasets reveal challenges in equitable deidentification.

Open source suite facilitates reproducibility and further research.

Abstract

The Collaborative Research Cycle (CRC) is a National Institute of Standards and Technology (NIST) benchmarking program intended to strengthen understanding of tabular data deidentification technologies. Deidentification algorithms are vulnerable to the same bias and privacy issues that impact other data analytics and machine learning applications, and can even amplify those issues by contaminating downstream applications. This paper summarizes four CRC contributions: theoretical work on the relationship between diverse populations and challenges for equitable deidentification; public benchmark data focused on diverse populations and challenging features; a comprehensive open source suite of evaluation metrology for deidentified datasets; and an archive of more than 450 deidentified data samples from a broad range of techniques. The initial set of evaluation results demonstrate the value of these tools for investigations in this field.