Quantification of a Privacy Preserving Data Mining Transformation

Data mining, with its promise to extract valuable, previously unknown and potentially useful patterns or knowledge from large data sets that contain private information is vulnerable to misuse. To protect the private or sensitive information, many privacypreserving data mining (PPDM) techniques have emerged. A large fraction of these techniques use randomized data distortion by adding noise from a known distribution function (e.g., uniform, normal) to the sensitive data. However, non-careful noise addition may introduce biases to the statistical parameters of these data. To preserve the statistical properties and meet privacy requirements of the sensitive data, we use a data transformation technique called Rotation

• Type: Conference
• Year: 2006
• Where: DMIN
• Authors: Mohammed Ketel
• Keywords: Data Mining, Data Transformation, DMIN 2006, DMIN 2007, Sensitive Data