Additive noise and multiplicative bias as disclosure limitation techniques for continuous microdata: A simulation study

Authors:
M. Trottini;S. E. Fienberg;U. E. Makov;M. M. Meyer
Affiliations:
(Corresponding author. Tel.: +34 9638 643 62/ Fax: +34 9638 647 35/ E-mail: mario.trottini@uv.es) Department of Statistics, University of Valencia, Valencia 46100, Spain;Department of Statistics and Center for Automated Learning and Discovery, Carnegie Mellon University, Pittsburgh, PA 15213, USA;Department of Statistics, Haifa university, Haifa 31905, Israel;Intelligent Results Inc., Bellevue, WA 98004, USA
Venue:
Journal of Computational Methods in Sciences and Engineering - Computational and Mathematical Methods for Science and Engineering Conference 2002 - CMMSE-2002
Year:
2004

Citing 1
Cited 3

Modelling user uncertainty for disclosure risk and data utility

International Journal of Uncertainty, Fuzziness and Knowledge-Based Systems

Random orthogonal matrix masking methodology for microdata release

International Journal of Information and Computer Security
Generic Probability Density Function Reconstruction for Randomization in Privacy-Preserving Data Mining

MLDM '07 Proceedings of the 5th international conference on Machine Learning and Data Mining in Pattern Recognition
Breaching Euclidean distance-preserving data perturbation using few known inputs

Data & Knowledge Engineering

Quantified Score

Hi-index	0.02

Visualization

Abstract

This paper focuses on a combination of two disclosure limitation techniques, additive noise and multiplicative bias, and studies their efficacy in protecting confidentiality of continuous microdata. A Bayesian intruder model is extensively simulated in order to assess the performance of these disclosure limitation techniques as a function of key parameters like the variability amongst profiles in the original data, the amount of users prior information, the amount of bias and noise introduced in the data. The results of the simulation offer insight into the degree of vulnerability of data on continuous random variables and suggests some guidelines for effective protection measures.