Statistical disclosure control in tabular data

Data disseminated by National Statistical Agencies (NSAs) can be classified as either microdata or tabular data. Tabular data is obtained from microdata by crossing one or more categorical variables. Although cell tables provide aggregated information, they also need to be protected. This chapter is a short introduction to tabular data protection. It contains three main sections. The first one shows the different types of tables that can be obtained, and how they are modeled. The second describes the practical rules for detection of sensitive cells that are used by NSAs. Finally, an overview of protection methods is provided, with a particular focus on two of them: “cell suppression problem” and “controlled tabular adjustment”.

[1]  Jordi Castro,et al.  Network Flows Heuristics for Complementary Cell Suppression: An Empirical Evaluation and Extensions , 2002, Inference Control in Statistical Databases.

[2]  Jordi Castro,et al.  A Shortest-Paths Heuristic for Statistical Data Protection in Positive Tables , 2007, INFORMS J. Comput..

[3]  Matteo Fischetti,et al.  Models and algorithms for the 2-dimensional cell suppression problem in statistical disclosure control , 1999, Math. Program..

[4]  Juan José SALAZAR-GONZÁLEZ.  Statistical confidentiality: Optimization techniques to protect tables , 2008 .

[6]  Neil E. Klepeis,et al.  User's and Programmer's Manual , 1994 .

[7]  Dale A. Robertson,et al.  Cell Suppression: Experience and Theory , 2002, Inference Control in Statistical Databases.

[8]  Juan-José Salazar-González,et al.  Controlled rounding and cell perturbation: statistical disclosure limitation methods for tabular data , 2006 .

[9]  Jordi Castro,et al.  A Fast Network Flows Heuristic for Cell Suppression in Positive Tables , 2004, Privacy in Statistical Databases.

[10]  Sarah Giessing,et al.  Tools and Strategies to Protect Multiples Tables with the GHQUAR Cell Suppression Engine , 2002, Inference Control in Statistical Databases.

[11]  L. H. Cox,et al.  Controlled rounding for tables with subtotals , 1989 .

[12]  Jordi Castro,et al.  An interior-point approach for primal block-angular problems , 2007, Comput. Optim. Appl..

[13]  James P. Kelly,et al.  Cell suppression: Disclosure protection for sensitive tabular data , 1992, Networks.

[14]  Jordi Castro,et al.  Quadratic interior-point methods in statistical disclosure control , 2005, Comput. Manag. Sci..

[15]  Jordi Castro,et al.  Using a Mathematical Programming Modeling Language for Optimal CTA , 2008, Privacy in Statistical Databases.

[16]  Lawrence H. Cox,et al.  Computational Aspects of Controlled Tabular Adjustment: Algorithm and Analysis , 2005 .

[17]  Jacques F. Benders,et al.  Partitioning procedures for solving mixed-variables programming problems , 2005, Comput. Manag. Sci..

[18]  Matteo Fischetti,et al.  Solving the Cell Suppression Problem on Tabular Data with Linear Constraints , 2001, Manag. Sci..

[19]  Josep Domingo-Ferrer,et al.  Statistical Databases , 2008, Wiley Encyclopedia of Computer Science and Engineering.

[20]  Jordi Castro,et al.  Minimum-distance controlled perturbation methods for large-scale tabular data protection , 2006, Eur. J. Oper. Res..

[21]  M. Bacharach.  Matrix Rounding Problems , 1966 .

[22]  Jordi Castro Pérez,et al.  Block coordinate descent decomposition for statistical data protection using controlled tabular adjustment , 2009 .

[23]  N. Dellaert,et al.  Statistical Disclosure in Two-Dimensional Tables: General Tables , 1994 .

[24]  Lawrence H. Cox,et al.  Network Models for Complementary Cell Suppression , 1995 .