Differential Inference Testing A Practical Approach to Evaluate Anonymized Data

Ali Kassem 1 Gergely Acs 2 Claude Castelluccia 3
1 COMETE - Concurrency, Mobility and Transactions
Inria Saclay - Ile de France, LIX - Laboratoire d'informatique de l'École polytechnique [Palaiseau]
3 PRIVATICS - Privacy Models, Architectures and Tools for the Information Society
Inria Grenoble - Rhône-Alpes, CITI - CITI Centre of Innovation in Telecommunications and Integration of services
Abstract : In order to protect individuals' privacy, governments and institutions impose some obligations on data sharing and publishing. Mainly, they require the data to be " anonymized ". In this paper, we shortly discuss the criteria introduced by European General Data Protection Regulation to assess anonymized data. We argue that the evaluation of anonymized data should be based on whether the data allows individual based inferences, instead of being centered around the concept of re-identification as the regulation has proposed. We then propose a framework that allows us to evaluate a given (anonymized) dataset. Finally, we apply our framework to evaluate two real datasets after being anonymized using k-anonymity and l-diversity techniques.
Document type :
Complete list of metadatas

Cited literature [18 references]  Display  Hide  Download

Contributor : Ali Kassem <>
Submitted on : Thursday, January 11, 2018 - 1:55:51 PM
Last modification on : Wednesday, March 27, 2019 - 4:41:28 PM
Long-term archiving on : Wednesday, May 23, 2018 - 5:52:53 PM


Files produced by the author(s)


  • HAL Id : hal-01681014, version 1


Ali Kassem, Gergely Acs, Claude Castelluccia. Differential Inference Testing A Practical Approach to Evaluate Anonymized Data. [Research Report] INRIA. 2018. ⟨hal-01681014v1⟩



Record views


Files downloads