/highdimensional-benchmark

A benchmark of anonymization methods for high-dimensional data provided by ARX

Primary LanguageJavaApache License 2.0Apache-2.0

A benchmark of anonymization methods for high-dimensional data implemented in ARX

Introduction

This repository implements a benchmark comparing the Lightning algorithm implemented in ARX with IGreedy and DataFly.

Setup

Please context us at arx.deidentifier@gmail.com for information on how to obtain the required input data. More information about the datasets is also available here.

Results

We have performed the experiments using a desktop machine with a quad-core 3.1 GHz Intel Core i5 CPU running a 64-bit Linux 3.2.0 kernel and a 64-bit Oracle JVM (1.7.0).

The results can be found in the respective folder.