Flexible data anonymization using ARX—Current status and challenges ahead

Abstract

The race for innovation has turned into a race for data. Rapid developments of new technologies, especially in the field of artificial intelligence, are accompanied by new ways of accessing, integrating, and analyzing sensitive personal data. Examples include financial transactions, social network activities, location traces, and medical records. As a consequence, adequate and careful privacy management has become a significant challenge. New data protection regulations, for example in the EU and China, are direct responses to these developments. Data anonymization is an important building block of data protection concepts, as it allows to reduce privacy risks by altering data. The development of anonymization tools involves significant challenges, however. For instance, the effectiveness of different anonymization techniques depends on context, and thus tools need to support a large set of methods to ensure that the usefulness of data is not overly affected by risk-reducing transformations. In spite of these requirements, existing solutions typically only support a small set of methods. In this work, we describe how we have extended an open source data anonymization tool to support almost arbitrary combinations of a wide range of techniques in a scalable manner. We then review the spectrum of methods supported and discuss their compatibility within the novel framework. The results of an extensive experimental comparison show that our approach outperforms related solutions in terms of scalability and output data quality-while supporting a much broader range of techniques. Finally, we discuss practical experiences with ARX and present remaining issues and challenges ahead.

Design and evaluation of a data anonymization pipeline to promote Open Science on COVID-19

“…This was achieved by always executing the pipeline on the complete primary file and holding back all records that do not fulfill the protection requirements defined. The pipeline was implemented using the open source ARX Data Anonymization Tool 20 .…”

Vallum-Med

“…However that must be balanced in order to avoid rendering the data useless for analysis. Vallum-Med uses as its data privacy tool ARX [8], a software for data obfuscation that also offers its resources through a public API. It performs the obfuscation of private data in datasets according to several privacy models such as: k-anonymity, ℓ-diversity, t-closeness, k-map, differential privacy, among others.…”

“…MariaDB was compiled as a SCONE container, in order to guarantee that it is safe during query processing. For the privacy module, we used the ARX Data Anonymization tool [8].…”

“…These patterns are set by the data owner for each sensitive or quasi-identifying attribute, through domain generalization hierarchies [8] that define valid values at each transformation level.…”

“…Vallum-Med is designed to leverage the TEE provided by Intel SGX technology using SCONE, and also deploys state-of-the-art data obfuscation techniques provided by the ARX tool [8].…”