Academia.eduAcademia.edu

Figure from:Hybrid Techniques for Data Privacy Preserving

See full PDFdownloadDownload figure
Table 7: Comparison between different Privacy preserving techniques Slicing overcomes the limitations of generalization and bucketization and preserves better utility while protecting against privacy threats. It is hard to learn sensitive information about an individual if you don’t even know whether this individual’s record is in the data or not. Thus from our study we analyzed that Slicing overcomes the limitations of existing techniques of generalization and bucketization and pre-serves better utility while protecting against privacy threats. Slicing protects attribute disclosure and membership disclosure. Slicing preserves better data utility than generalization and is more operative than bucketization regarding the sensitive attribute. Anonymization technique is powerful method for privacy preserving of published data. Overlap Slicing overcomes the limitations of slicing and preserves better utility while protecting against privacy threats. Overlapping slicing is used to prevent attribute disclosures and better membership disclosure. In the last Generalized Slicing protects membership, identity and attribute disclosure.

Table 7 Comparison between different Privacy preserving techniques Slicing overcomes the limitations of generalization and bucketization and preserves better utility while protecting against privacy threats. It is hard to learn sensitive information about an individual if you don’t even know whether this individual’s record is in the data or not. Thus from our study we analyzed that Slicing overcomes the limitations of existing techniques of generalization and bucketization and pre-serves better utility while protecting against privacy threats. Slicing protects attribute disclosure and membership disclosure. Slicing preserves better data utility than generalization and is more operative than bucketization regarding the sensitive attribute. Anonymization technique is powerful method for privacy preserving of published data. Overlap Slicing overcomes the limitations of slicing and preserves better utility while protecting against privacy threats. Overlapping slicing is used to prevent attribute disclosures and better membership disclosure. In the last Generalized Slicing protects membership, identity and attribute disclosure.

Related Figures (5)

Generalization is one of the most common anonymization technique, which replaces quasi- identifier values with values that are less-specific but semantically consistent. Then, all quasi- identifier values in a group would be generalized to the entire group extent in the QID space. If at least two transactions in a group have distinct values in a certain column (i.e. one contains an item and the other does not), then all information about that item in the current group is lost. Due to the high- dimensionality of the quasi-identifier, with the number of possible items in the order of thousands, it is likely that any generalization method would have extremely high information loss, leaving data useless. In order for generalization to be effective, records in the same bucket must be close to each other so that generalizing the records would not lose too much information.
Generalization is one of the most common anonymization technique, which replaces quasi- identifier values with values that are less-specific but semantically consistent. Then, all quasi- identifier values in a group would be generalized to the entire group extent in the QID space. If at least two transactions in a group have distinct values in a certain column (i.e. one contains an item and the other does not), then all information about that item in the current group is lost. Due to the high- dimensionality of the quasi-identifier, with the number of possible items in the order of thousands, it is likely that any generalization method would have extremely high information loss, leaving data useless. In order for generalization to be effective, records in the same bucket must be close to each other so that generalizing the records would not lose too much information.
Limitation of Generalization:
Limitation of Generalization:
Generalized-Slicing works in three main steps
Generalized-Slicing works in three main steps