• DESIGN AND DEVELOPMENT OF SANITIZATION ALGORITHM FOR MINING PRIVACY - PRESERVING FREQUENT ITEMSETS
Abstract
ABSTRACT
Data mining services require accurate input data for their results to be meaningful, but privacy concerns may influence users to provide spurious information. In order to preserve the privacy of the client in data mining process, a variety of techniques based on random perturbation of data records have been proposed recently. In this paper we concentrate on Data sanitization problem by providing a Non-uniform Randomized sanitization algorithm for sanitizing the original database to transform it into a sanitized database devoid of any sensitive patterns specified by the data owner. The Uniform randomized sanitization algorithm considers any item in a restricted itemset as a victim item to be removed from sensitive transactions with an equal probability. But the Non-uniform Randomized sanitization algorithm prefers items with high support as victim items, thereby minimizing the effect on non-sensitive patterns. As a result accuracy will be increased.
Keywords-frequent patterns, sensitive patterns, non-sensitive patterns, legitimate patterns, sanitization, privacy preserving
Data mining services require accurate input data for their results to be meaningful, but privacy concerns may influence users to provide spurious information. In order to preserve the privacy of the client in data mining process, a variety of techniques based on random perturbation of data records have been proposed recently. In this paper we concentrate on Data sanitization problem by providing a Non-uniform Randomized sanitization algorithm for sanitizing the original database to transform it into a sanitized database devoid of any sensitive patterns specified by the data owner. The Uniform randomized sanitization algorithm considers any item in a restricted itemset as a victim item to be removed from sensitive transactions with an equal probability. But the Non-uniform Randomized sanitization algorithm prefers items with high support as victim items, thereby minimizing the effect on non-sensitive patterns. As a result accuracy will be increased.
Keywords-frequent patterns, sensitive patterns, non-sensitive patterns, legitimate patterns, sanitization, privacy preserving
Keywords
Keywords-frequent patterns, sensitive patterns, non-sensitive patterns, legitimate patterns, sanitization, privacy preserving
Full Text:
PDFThis work is licensed under a Creative Commons Attribution-NonCommercial-ShareAlike 4.0 International License.
© 2010-2022 International Journal of Mathematical Archive (IJMA) Copyright Agreement & Authorship Responsibility |