Mitigating the ICA Attack Against Rotation-Based Transformation for Privacy Preserving Clustering

Free registration required

Executive Summary

The Rotation-Based Transformation (RBT) for privacy preserving data mining is vulnerable to the Independent Component Analysis (ICA) attack. This paper introduces a modified multiple-rotation-based transformation technique for special mining applications, mitigating the ICA attack while maintaining the advantages of the RBT. While it is important for data owners to publish their data to a third party to provide data mining services, the privacy of the data itself needs to be maintained. Therefore, several perturbation methods have been introduced considering potential applications. One of these methods is Rotation-Based Transformation (RBT) in which the data is transformed geometrically while the distance between the data points is preserved.

  • Format: PDF
  • Size: 237.7 KB