Multidimensional k-Anonymization by Linear Clustering Using Space-Filling Curves
Fu, Ada Wai-Chee, Lo, C.S., Pei, Jian, Wan, Steven Chi-Wen, Wang, Ke, Wong, Raymond Chi-Wing · Rare & Special e-Zone (The Hong Kong University of Science and Technology) · 2006
Anonymization has been well-recognized as an effective approach to protect privacy. In this paper, we study the problem of k-anonymization of numeric data. We propose a simple yet effective approach to this problem. We transform a data set with a multidimensional numeric quasi-identifier into a data set with a one-dimensional numeric quasi-identi er using space-filling curves. Effecacious algorithms are proposed to compute the k-anonymization on the transformed data set. The k-anonymized data set is then transformed back to the original multidimensional space with the k-anonymity preserved. Our empirical studies on both real data sets and synthetic data sets show that, compared to the state-of-the-art methods, our method achieves a smaller distortion and is more efficient and scalable.