VICUS: a noise addition technique for categorical data

Authors:
Helen Giggins;Ljiljana Brankovic
Affiliations:
The University of Newcastle, Callaghan, NSW, Australia;The University of Newcastle, Callaghan, NSW, Australia
Venue:
AusDM '12 Proceedings of the Tenth Australasian Data Mining Conference - Volume 134
Year:
2012

Citing 14
Cited 2

A combinatoral problem in database security

Discrete Applied Mathematics
An Optimization Problem in Statistical Databases

SIAM Journal on Discrete Mathematics
ROCK: a robust clustering algorithm for categorical attributes

Information Systems
Computers and Intractability: A Guide to the Theory of NP-Completeness

Computers and Intractability: A Guide to the Theory of NP-Completeness
Genetic Algorithm and Graph Partitioning

IEEE Transactions on Computers
Data Swapping: Balancing Privacy against Precision in Mining for Logic Rules

DaWaK '99 Proceedings of the First International Conference on Data Warehousing and Knowledge Discovery
Usability of Compromise-Free Statistical Databases

SSDBM '97 Proceedings of the Ninth International Conference on Scientific and Statistical Database Management
2-Compromise Usability in 1-Dimensional Statistical Databases

COCOON '02 Proceedings of the 8th Annual International Conference on Computing and Combinatorics
k-anonymity: a model for protecting privacy

International Journal of Uncertainty, Fuzziness and Knowledge-Based Systems
A theoretical basis for perturbation methods

Statistics and Computing
L-diversity: Privacy beyond k-anonymity

ACM Transactions on Knowledge Discovery from Data (TKDD)
The cost of privacy: destruction of data-mining utility in anonymized data publishing

Proceedings of the 14th ACM SIGKDD international conference on Knowledge discovery and data mining
Differential privacy

ICALP'06 Proceedings of the 33rd international conference on Automata, Languages and Programming - Volume Part II
Calibrating noise to sensitivity in private data analysis

TCC'06 Proceedings of the Third conference on Theory of Cryptography

Missing value imputation using decision trees and decision forests by splitting and merging records: Two novel techniques

Knowledge-Based Systems
FIMUS: A framework for imputing missing values using co-appearance, correlation and similarity analysis

Knowledge-Based Systems

Quantified Score

Hi-index	0.00

Visualization

Abstract

Privacy preserving data mining and statistical disclosure control have received a great deal of attention during the last few decades. Existing techniques are generally classified as restriction and data modification. Within data modification techniques noise addition has been one of the most widely studied but has traditionally been applied to numerical values, where the measure of similarity is straightforward. In this paper we introduce VICUS, a novel privacy preserving technique that adds noise to categorical data. Experimental evaluation indicates that VICUS performs better than random noise addition both in terms of security and data quality.