Practice of Disclosure Limitation Techniques

disclosure limitation;risk;microdata;synthetic;noise;data swapping;differential privacy;perturbation;Applied Mathematics & Statistics

Shen, Lu

Johns Hopkins University

关键词: disclosure limitation;    risk;    microdata;    synthetic;    noise;    data swapping;    differential privacy;    perturbation;    Applied Mathematics & Statistics;   

Others  :  https://jscholarship.library.jhu.edu/bitstream/handle/1774.2/37285/SHEN-THESIS-2014.pdf?sequence=1&isAllowed=y

瑞士|英语

来源: JOHNS HOPKINS DSpace Repository

【 摘 要 】

In recent years, there has been increasing concern about the identification of personal or corporate information in published data; the privacy issue. Much of this interest has been focused on issues relating to release of micro (e.g., patient-specific) and tabulated data.Increasingly, people ask: ;;Does de-identification work or not?;; In this project we review a subset ofthe currentdisclosure limitation methods,including suppression and aggregation, swapping, random noise and synthetic data. Then, we assess the performance and disclosure risk associated witha few of themethods. To accomplish this, we use the microdata collected by the PREMIER Collaborative Research Group. Specifically, random noise and synthetic data methods are evaluated by comparing the results obtained from the modified data with those obtained from micro data. Furthermore, we compare the modified data in regards to disclosure risk using alpha/beta measures and differential privacy method.