Density-based microaggregation for statistical disclosure control

Lin, Jun-Lin; Wen, Tsung-Hsien; Hsieh, Jui-Chien; Chang, Pei‐Chann

doi:10.1016/j.eswa.2009.09.054

Cited by 57 publications

(55 citation statements)

References 25 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Any remaining records are then added to their respective nearest clusters. Experimental results indicate that MDAV-1 incurs slightly less information loss than MDAV [29]. Another variant of the MDAV method, called MDAV-generic, is proposed by Domingo-Ferrer and Torra [8], where by the threshold 2k is altered to 3k.…”

Section: Previous Microaggregation Methodsmentioning

confidence: 99%

“…For fixed-size microaggregation, the partition is done by dividing a dataset into clusters that have size k, except perhaps one cluster which has a size between k and (2k − 1), depending on the total number of records n and the anonymity parameter k. For the data-oriented microaggregation, the partition is done by allowing all clusters with sizes between k and (2k − 1). Intuitively, fixed-size methods reduce the search space, and thus are more computationally efficient than data-oriented methods [29]. However, data-oriented methods can adapt to different values of k and various data distributions and thus may achieve lower information loss than fixed-size methods.…”

Section: Previous Microaggregation Methodsmentioning

confidence: 99%

“…So MDAV is a fixed size method. Lin et al [29] proposed a modified MDAV, called MDAV-1. The MDAV-1 is similar to MDAV except when the number of the remaining records is between k and (2k − 1), a new cluster is formed with the record that is the furthest from the centroid of the remaining records, and its (k − 1) nearest records.…”

Section: Previous Microaggregation Methodsmentioning

confidence: 99%

“…Lin et al [29] proposed a density-based algorithm (DBA) for microaggregation. The DBA has two different scenarios.…”

Section: Previous Microaggregation Methodsmentioning

confidence: 99%

“…Notable examples include Maximum Distance [15], Diameter-based Fixed-Size microaggregation and centroid-based Fixed-size microaggregation [13], Maximum Distance to Average Vector (MDAV) [8], MHM [9] and the Two Fixed Reference Points method [28]. Most recently, Lin et al [29] proposed a density-based microaggregation method that forms clusters by the descending order of their densities, and then fine-tunes these clusters in reverse order.…”

Section: Introductionmentioning

confidence: 99%

See 4 more Smart Citations

New Multi-dimensional Sorting Based K-Anonymity Microaggregation for Statistical Disclosure Control

Mahmood

Kabir

Mustafa

2013

Lecture Notes of the Institute for Computer Sciences, Social Informatics and Telecommunications Engineering

View full text Add to dashboard Cite

Abstract. In recent years, there has been an alarming increase of online identity theft and attacks using personally identifiable information. The goal of privacy preservation is to de-associate individuals from sensitive or microdata information. Microaggregation techniques seeks to protect microdata in such a way that can be published and mined without providing any private information that can be linked to specific individuals. Microaggregation works by partitioning the microdata into groups of at least k records and then replacing the records in each group with the centroid of the group. An optimal microaggregation method must minimize the information loss resulting from this replacement process. The challenge is how to minimize the information loss during the microaggregation process. This paper presents a new microaggregation technique for Statistical Disclosure Control (SDC). It consists of two stages. In the first stage, the algorithm sorts all the records in the data set in a particular way to ensure that during microaggregation very dissimilar observations are never entered into the same cluster. In the second stage an optimal microaggregation method is used to create k-anonymous clusters while minimizing the information loss. It works by taking the sorted data and simultaneously creating two distant clusters using the two extreme sorted values as seeds for the clusters. The performance of the proposed technique is compared against the most recent microaggregation methods. Experimental results using benchmark datasets show that the proposed algorithm has the lowest information loss compared with a basket of techniques in the literature.

show abstract

Section: Previous Microaggregation Methodsmentioning

confidence: 99%

Section: Previous Microaggregation Methodsmentioning

confidence: 99%

Section: Previous Microaggregation Methodsmentioning

confidence: 99%

“…Lin et al [29] proposed a density-based algorithm (DBA) for microaggregation. The DBA has two different scenarios.…”

Section: Previous Microaggregation Methodsmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

See 3 more Smart Citations

New Multi-dimensional Sorting Based K-Anonymity Microaggregation for Statistical Disclosure Control

Mahmood

Kabir

Mustafa

2013

Lecture Notes of the Institute for Computer Sciences, Social Informatics and Telecommunications Engineering

View full text Add to dashboard Cite

show abstract

Towards publishing directed social network data with k‐degree anonymization

Lin

Xiao

2022

Concurrency and Computation

View full text Add to dashboard Cite

Anonymization is a practical solution for preserving user's identity privacy before data publishing. There are various anonymity techniques can be applied to maintain data utility of micro-data and social networks, however these methods lead to a high runtime or low anonymous graph utility. In this article, an efficient, utility-preserving approach has been proposed to reduce anonymization runtime as well as the amount of information loss incurred by graph anonymization. We craft our anonymization algorithm by combining greedy partition-based aggregating with multi-dimensional sorting as main heuristic tools. The proposed algorithm generates a partial order of the vertices so that the vertex at top rank and another vertex at bottom rank can never be aggregated in the same group, the runtime is reduced. Greedy partition-based aggregating is employed to create k-anonymous clusters which minimizing information loss. Experimental results on real-world datasets show the proposed method has good performance and is superior to the existing methods.

show abstract

An Efficient Microaggregation Method for Protecting Mixed Data

Chettri¹,

Borah

2013

Lecture Notes in Electrical Engineering

View full text Add to dashboard Cite

Density-based microaggregation for statistical disclosure control

Cited by 57 publications

References 25 publications

New Multi-dimensional Sorting Based K-Anonymity Microaggregation for Statistical Disclosure Control

New Multi-dimensional Sorting Based K-Anonymity Microaggregation for Statistical Disclosure Control

Towards publishing directed social network data with k‐degree anonymization

An Efficient Microaggregation Method for Protecting Mixed Data

Contact Info

Product

Resources

About