A survey on statistical disclosure control and micro‐aggregation techniques for secure statistical databases

Abstract

This paper surveys the fields of Statistical Disclosure Control (SDC) and Micro‐Aggregation Techniques (MATs), which are both areas fundamental to the science of secure Statistical DataBases (SDBs). The paper is written from the perspective of a computer scientist with the hope that it will prove to be a source of reference material useful to researchers and practitioners in the field. The paper first introduces the concept of SDC and describes the domain of its applications and the various data types that are currently used in SDBs. It then proceeds to focus on the family of micro‐data types in SDBs. At this juncture, we introduce the importance of the relevant measures, namely the metrics termed as the Information Loss (IL) and the Disclosure Risk (DR), after which we survey the various methods of resolving the conflicting goals that these metrics represent. Thereafter, the paper summarizes the perturbative and non‐perturbative SDC methods for micro‐data protection, and it focuses on the families of MATs by formally stating the Micro‐Aggregation Problem and surveying it in a comprehensive manner. Apart from the paper including a historical view of the field of MATs, it describes a broad selection of work that has been reported more recently. Indeed, we believe that this paper represents a complete overview of the state‐of‐the‐art techniques. Copyright © 2010 John Wiley & Sons, Ltd.

Statistical Disclosure Limitation in the Presence of Edit Rules

“…Larger cluster sizes result in greater data perturbation. To construct clusters, one can project data onto a single dimension, for example, using the first principal component or the sum of z-scores (Fayyoumi and Oommen 2010). Alternatively, one can find the clusters using a heuristic based on Euclidean distances between records.…”

On Utilizing Association and Interaction Concepts for Enhancing Microaggregation in Secure Statistical Databases

“…Unlike in ACNN, in our solution, we do not compute the sum of all the interactions between the nodes but rather need the one that maximally interacts with the nodes that are already in the same cluster, e.g., X i and X j . Thus, as explained in [33], we advocate the use of semiring transitive closure properties similar to a matrix multiplication scheme that is central in determining the multistep Markov matrix for a Markov chain. 4) The final difference between our scheme and ACNN is the fact that we have resorted to a one-shot "training" mechanism, 3 which is atypical for most NNs but was used in [1].…”

“…4) The final difference between our scheme and ACNN is the fact that we have resorted to a one-shot "training" mechanism, 3 which is atypical for most NNs but was used in [1]. Details of this mechanism are also found in [33] and were omitted here for brevity. Based on the aforementioned principles, we now present the design of our newly proposed IAMAT scheme.…”

MDAV2K: A Variable-Size Microaggregation Technique for Privacy Preservation

“…Microaggregation is a perturbative technique for microdata (i.e individual records) protection appearing in statistical disclosure control [3]. Given a dataset, it builds small groups of at least k records, with k being a user-definable parameter.…”