Statistical Disclosure Control

There are two main approaches to SDC: principles-based and rules-based. In principles-based systems, disclosure control attempts to upload a specific set of fundamental principles---for example, "no person should be identifiable in released microdata." Rules-based systems, in contrast, are evidenced by a specific set of rules that a person performing disclosure control follows, after which the data are presumed to be safe to release. Using this taxonomy, proposed by Ritchie and Elliot in 2013, disclosure control based on differential privacy can be seen as a principles-based approach, whereas controls based on de-identification, such as the US Health Insurance Portability and Accountability Act's Privacy Rule's Safe Harbor method for de-identifying Protected health information can be seen as a rule-based system.

Presentations

• Disclosure Avoidance Methods and Research at the U. S. Census Bureau, Billy Wisniewski, Amy Lauger, and Laura McKenna, Center for Disclosure Avoidance, Research (CDAR), U.S. Census Bureau, April 21, 2015

• eConfidentiality - a Disclosure Avoidance Application System (Proposed), Bei Wang, U.S. Census Bureau, April 21, 2015

How-to Guides

• Statistical Policy Working Paper 22, Federal Committee on Statistical Methodology, Originally Prepared by Subcommittee on Disclosure Limitation Methodology 1994 Revised by Confidentiality and Data Access Committee 2005

• Differential Privacy: A Primer for a non-technical auidence, Kobbi Nissim and Alexandra Wood, Presented at the CDAC 2017 Workshop on New Advances in Disclosure Limitation, Sept. 27, 2017

Papers

US Census Bureau

Below are papers that the US Census Bureau has written on statistical Disclosure Control

• “Examples of Easy-to-implement, Widely Used Masking Methods for which Analytic Properties are not Justified,” Winkler, W. E. (2007b),
• Disclosure Avoidance Techniques at the U.S. Census Bureau: Current Practices and Research, Amy Lauger, Billy Wisniewski, and Laura McKenna, Center for Disclosure Avoidance Research, RESEARCH REPORT SERIES #2014-02, U.S. Census Bureau, September 26, 2014.
• Disclosure Avoidance Practices and Research at the U.S. Census Bureau: An Update, Laura Zayatz, Statistical Research Division, RESEARCH REPORT SERIES, (Statistics #2005-06), Revised August 31, 2005
• Disclosure, U.S. Census Bureau Economic Census website, Last Revised: March 05, 2015
• Disclosure Avoidance for Census 2010 and American Community Survey Five-year Tabular Data Products , Laura Zayatz, Jason Lucero, Paul Massell, Asoka Ramanayake, RESEARCH REPORT SERIES (Statistics #2009-10) , November 23, 2009
• A Monograph on Confidentiality and Privacy in the U.S. Census, George Gatewood, US Census Policy Office, July 2001.
• A Disclosure Avoidance Research Agenda, Paul B. Massell, Center for Disclosure Avoidance Research, U.S. Census Bureau, May 2014.
• Winkler, W. E. (2008), “General Discrete-data Modeling Methods for Producing Synthetic Data with Reduced Re-identification Risk that Preserve Analytic Properties,” IAB Workshop on Confidentiality and Disclosure, http://fdz.iab.de/en/FDZ_Events/SDC-Workshop.aspx, Nuremberg, Germany, November 20-21, 2008 (also http://www.census.gov/srd/papers/pdf /rrs2010-02 ).
• Winkler, W. E. (2010), “General Discrete-data Modeling Methods for Creating Synthetic Data with Reduce Re-identification Risk that Preserve Analytic Properties,” http://www.census.gov/srd/papers/pdf/rrs2010-02.pdf .
• Winkler, W.E. (2013c), Cleanup and Analysis of Sets of National Files, Federal Committee on Statistical Methodology, Proceedings of the Bi-Annual Research Conference, http://www.copafs.org/UserFiles/file/fcsm/J1_Winkler_2013FCSM.pdf., https://fcsm.sites.usa.gov/files/2014/05/J1_Winkler_2013FCSM.pdf

Review Articles

• Fienberg, Stephen, "Confidentiality and Disclosure Limitation," Encyclopedia of Social Measurement, Volume 1, 2005. A good overview article about statistical disclosure limitation, not too much math. No mention of differential privacy, of course.

Critiques

Many contemporary statistical disclosure control techniques, such as generalization and cell suppression, have been shown to be vulnerable to attack by a hypothetical data intruder. For example, Cox showed in 2009 that Complementary cell suppression typically leads to "over-protected" solutions because of the need to suppress both primary and complementary cells, and even then can lead to the compromise of sensitive data when exact intervals are reported.