CRCYDBJan 8, 2020

Techniques d'anonymisation tabulaire : concepts et mise en oeuvre

arXiv:2001.02650v1
AI Analysis

It provides an incremental tutorial for technical audiences to understand and apply data anonymization methods.

This paper presents a state-of-the-art overview of anonymization techniques for tabular datasets, aimed at explaining concepts to sanitize data and compute reidentification risks with numerous examples.

In this document, we present a state of the art of anonymization techniques for classical tabular datasets. This article is geared towards a general public having some knowledge of mathematics and computer science, but with no need for specific knowledge in anonymization. The objective of this document it to explain anonymization concepts in order to be able to sanitize a dataset and compute reindentification risk. The document contains a large number of examples to help understand the calculations. ----- Dans ce document, nous présentons l'état de l'art des techniques d'anonymisation pour des bases de données classiques (i.e. des tables), à destination d'un public technique ayant une formation universitaire de base en mathématiques et informatique, mais non spécialiste. L'objectif de ce document est d'expliquer les concepts permettant de réaliser une anonymisation de données tabulaires, et de calculer les risques de réidentification. Le document est largement composé d'exemples permettant au lecteur de comprendre comment mettre en oeuvre les calculs.

Foundations

The foundational work for this paper's niche, ranked by how specifically the neighbourhood builds on it — not by global fame.

Your Notes