Noise Infusion as a Confidentiality Protection Measure for Graph-Based Statistics

17 Pages Posted: 13 Nov 2014

See all articles by John M. Abowd

John M. Abowd

U.S. Census Bureau; Cornell University Department of Economics; Labor Dynamics Institute; School of Industrial and Labor Relations; NBER (on leave); CREST; IZA Institute of Labor Economics

Kevin L McKinney

University of California, Los Angeles (UCLA)

Date Written: September 01, 2014

Abstract

We use the bipartite graph representation of longitudinally linked employer-employee data, and the associated projections onto the employer and employee nodes, respectively, to characterize the set of potential statistical summaries that the trusted custodian might produce. We consider noise infusion as the primary confidentiality protection method. We show that a relatively straightforward extension of the dynamic noise-infusion method used in the U.S. Census Bureau’s Quarterly Workforce Indicators can be adapted to provide the same confidentiality guarantees for the graph-based statistics: all inputs have been modified by a minimum percentage deviation (i.e., no actual respondent data are used) and, as the number of entities contributing to a particular statistic increases, the accuracy of that statistic approaches the unprotected value. Our method also ensures that the protected statistics will be identical in all releases based on the same inputs.

Suggested Citation

Abowd, John Maron and McKinney, Kevin L, Noise Infusion as a Confidentiality Protection Measure for Graph-Based Statistics (September 01, 2014). US Census Bureau Center for Economic Studies Paper No. CES-WP- 14-30. Available at SSRN: https://ssrn.com/abstract=2523446 or http://dx.doi.org/10.2139/ssrn.2523446

John Maron Abowd (Contact Author)

U.S. Census Bureau ( email )

4600 Silver Hill Road
Washington, DC 20233
United States
+1.301.763.5880 (Phone)

Cornell University Department of Economics ( email )

261 Ives Hall
Ithaca, NY 14853-3901
United States

HOME PAGE: http://www.economics.cornell.edu

Labor Dynamics Institute ( email )

Ithaca, NY 14853-3901
United States

HOME PAGE: http://www.ilr.cornell.edu/LDI/

School of Industrial and Labor Relations ( email )

Ithaca, NY 14853-3901
United States

HOME PAGE: http://www.ilr.cornell.edu/LDI/

NBER (on leave) ( email )

1050 Massachusetts Avenue
Cambridge, MA 02138
United States

CREST ( email )

92245 Malakoff Cedex
France

HOME PAGE: http://www.crest.fr/

IZA Institute of Labor Economics

P.O. Box 7240
Bonn, D-53072
Germany

Kevin L McKinney

University of California, Los Angeles (UCLA) ( email )

405 Hilgard Avenue
Box 951361
Los Angeles, CA 90095
United States

Register to save articles to
your library

Register

Paper statistics

Downloads
11
Abstract Views
219
PlumX Metrics