Data publishing is a challenging task for privacy preservation constraints. To ensure privacy, many anonymization techniques have been proposed. They differ in terms of the mathematical properties they verify and in terms of the functional objectives expected. Disassociation is one of the techniques that aim at anonymizing of set-valued datasets (e.g., discrete locations, search and shopping items) while guaranteeing the confidentiality property known as $k^m$ -anonymity. Disassociation separates the items of an itemset in vertical chunks to create ambiguity in the original associations. In a previous work, we defined a new ant-based clustering algorithm for the disassociation technique to preserve some items associated together, called utility rules, throughout the anonymization process, for accurate analysis. In this paper, we examine the disassociated dataset in terms of knowledge extraction. To make data analysis easy on top of the anonymized dataset, we define neighbor datasets or in other terms datasets that are the result of a probabilistic re-association process. To assess the neighborhood notion set-valued datasets are formalized into trees and a tree edit distance (TED) is directly applied between these neighbors. Finally, we prove the faithfulness of the neighbors to knowledge extraction for future analysis, in the experiments.

Disassociation introduced by Terrovitis et al. is a bucketization based anonimyzation technique that divides a set-valued dataset into several clusters to hide the link between individuals and their complete set of items. It increases the utility of the anonymized dataset, but on the other side, it raises many privacy concerns, one in particular, is when the items are tightly coupled to form what is called, a cover problem. In this paper, we present safe disassociation, a technique that relies on partial-suppression, to overcome the aforementioned privacy breach encountered when disassociating set-valued datasets. Safe disassociation allows the $k^m$-anonymity privacy constraint to be extended to a bucketized dataset and copes with the cover problem. We describe our algorithm that achieves the safe disassociation and we provide a set of experiments to demonstrate its efficiency.