We consider group-based anonymized tables, a popular approach to data publishing. This approach aims at protecting privacy of the involved individuals, by releasing an obfuscated version of the original data, where the exact correspondence between individuals and attribute values is hidden. When publishing data about individuals, one must typically balance the learner's utility against the risk posed by an attacker, potentially targeting individuals in the dataset. Accordingly, we propose a mcmc based methodology by which a data curator can simultaneously: (a) learn the population parameters from a given anonymized table, thus assessing its utility; (b) analyze the risk for any individual in the dataset to be linked to a specific sensitive value, beyond what can be inferred from the population parameters learned in (a), when the attacker has got to know the individual's nonsensitive attributes. We call this relative risk analysis. We propose a unified probabilistic model that encompasses both horizontal group based anonymization schemes, such as k-anonymity, and vertical ones, such as Anatomy. We detail the learning procedure for both the honest learner and the attacker. Based on the learned distributions, we put forward relative risk measures. Finally, we illustrate some experiments conducted with the proposed methodology on a real world dataset
Relative privacy risks and learning from anonymized data / Boreale, Michele; Corradi, Fabio. - ELETTRONICO. - (2017), pp. 0-0.
Relative privacy risks and learning from anonymized data
BOREALE, MICHELE;CORRADI, FABIO
2017
Abstract
We consider group-based anonymized tables, a popular approach to data publishing. This approach aims at protecting privacy of the involved individuals, by releasing an obfuscated version of the original data, where the exact correspondence between individuals and attribute values is hidden. When publishing data about individuals, one must typically balance the learner's utility against the risk posed by an attacker, potentially targeting individuals in the dataset. Accordingly, we propose a mcmc based methodology by which a data curator can simultaneously: (a) learn the population parameters from a given anonymized table, thus assessing its utility; (b) analyze the risk for any individual in the dataset to be linked to a specific sensitive value, beyond what can be inferred from the population parameters learned in (a), when the attacker has got to know the individual's nonsensitive attributes. We call this relative risk analysis. We propose a unified probabilistic model that encompasses both horizontal group based anonymization schemes, such as k-anonymity, and vertical ones, such as Anatomy. We detail the learning procedure for both the honest learner and the attacker. Based on the learned distributions, we put forward relative risk measures. Finally, we illustrate some experiments conducted with the proposed methodology on a real world datasetFile | Dimensione | Formato | |
---|---|---|---|
3407_11724 [Pages 225 - 230].pdf
accesso aperto
Descrizione: Contributo nel volume dei proceddengs
Tipologia:
Pdf editoriale (Version of record)
Licenza:
Open Access
Dimensione
171.12 kB
Formato
Adobe PDF
|
171.12 kB | Adobe PDF |
I documenti in FLORE sono protetti da copyright e tutti i diritti sono riservati, salvo diversa indicazione.