30-07-2014, 03:52 PM
SLICING:A NEW APPROACH FOR PRIVACY
PRESERVING DATA PUBLISHING
SLICING.pdf (Size: 222.52 KB / Downloads: 11)
ABSTRACT
• Privacy preservation is important one while publishing the
information.
• Generally sensitive information about individual’s records will
violate the privacy.
• Anonymization techniques:
1. Generalization
2. Bucketization
• both technique used for privacy preserving microdata
publishing and also have some limitations,to overcome that
we introduce new approach called SLICING.
INTRODUCTION
• Several micro data anonymization techniques have been
proposed:
1. Generalization for k-anonymity
2. Bucketization for l-diversity
• In both approaches, attributes are partitioned into three
categories:
• Identifiers
• Quasi-identifiers
• sensitive attributes
CONT...
• Bucketization
• Do not prevent membership disclosure
• Unclear separation in QI & SA
• By separation it breakes the correlation between QI & SA
• To overcome those drawbacks we introduce new
anonymization technique called SLICING.
RELATED WORK
Generalization:
• 3 types of encoding schemes:
1. Global recoding
2. Regional recoding
3. Local recoding
• Local recoding:
• Allows different occurences of the same value to be
generalized differently.
CONCLUSION
• Here a new approach called slicing is introduced to privacy
preserving microdata publishing.
• Slicing overcomes the limitations of generalization and
bucketization and preserves better utility while protecting
against privacy threats.
• Reduces the dimensionality of data
• Slicing is a promising technique for handling high-dimensional
data.