Information Security and Privacy in Smart Devices: Tools, Methods, and Applications by Rabadão Carlos

Author:Rabadão Carlos
Language: eng
Format: epub
Publisher: Information Science Reference

Anonymization algorithms are applied on the QID values to prevent the intruder from causing privacy threat. Therefore, the privacy goal of any anonymization algorithms is to prevent the privacy threats.

Utility Goal

With data anonymization there is difference between the original data and the anonymized data, this is called as information loss. To prevent privacy threats, the data is anonymized and there is an information loss, but it should be minimal to have greater utility of the published data. There must be balance between the privacy preservation and information loss (Martin et al., 2007).

In this paper the privacy and utility goals of fifteen algorithms is discussed.

Definitions

Let T be the original microdata table, in the published microdata the identifiers are removed and anonymization methods are applied on Quasi-Identifier’s. The resulting table is of the form: T` (QID’s, SA’s).

· Definition 1: Equivalence Class (EQ)- An EQ is a set of anonymized records that have same QID attribute values. The records in an EQ are all identical with respect to their QID values.

· Definition 2: k-anonymity (Ciriani et al., n.d.)- A table satisfies k-anonymity if the records in an EQ are indistinguishable from other (k-1) records with reference to QID attributes.

· Definition 3: l-diversity (Machanavajjhala et al., 2007; Xiao et al., 2010; Kifer & Gehrke, 2006a)- An EQ is said to satisfy l-diversity if there are at least l “well represented” values for SA’s.

· Definition 4: t-closeness (Li, 2007)- A EQ is said to satisfy t-closeness if the distance between the distribution of a SA within any EQ and the distribution of the same attribute in the entire table is not more than the predefined threshold ‘t’.

· Definition 5: Privacy Threat (Sowmyarani and Dayananda, n.d.)- A threat that is caused by an intruder after gaining access to the published data and is able to link the record of the respondent with his sensitive attribute. The threat may be in physical or informational.

Download

Copyright Disclaimer:
This site does not store any files on its server. We only index and link to content provided by other sites. Please contact the content providers to delete copyright contents if any and email us, we'll remove relevant links or contents immediately.