Privacy-Preserving k-means Clustering of Encrypted Data

Vol. 28, No. 6, pp. 1401-1414, Nov. 2018
10.13089/JKIISC.2018.28.6.1401, Full Text:
Keywords:
Abstract

The k-means clustering algorithm groups input data with the number of groups represented by variable k. In fact, thisalgorithm is particularly useful in market segmentation and medical research, suggesting its wide applicability. In this paper,we propose a privacy-preserving clustering algorithm that is appropriate for outsourced encrypted data, while exposing noinformation about the input data itself. Notably, our proposed model facilitates encryption of all data, which is a largeadvantage over existing privacy-preserving clustering algorithms which rely on multi-party computation over plaintext datastored on several servers. Our approach compares homomorphically encrypted ciphertexts to measure the distance betweeninput data. Finally, we theoretically prove that our scheme guarantees the security of input data during computation, and alsoevaluate our communication and computation complexity in detail.

Statistics
Show / Hide Statistics

Statistics (Cumulative Counts from December 1st, 2017)
Multiple requests among the same browser session are counted as one view.
If you mouse over a chart, the values of data points will be shown.


Cite this article
[IEEE Style]
정윤송, 김준식, 이동훈, "Privacy-Preserving k-means Clustering of Encrypted Data," Journal of The Korea Institute of Information Security and Cryptology, vol. 28, no. 6, pp. 1401-1414, 2018. DOI: 10.13089/JKIISC.2018.28.6.1401.

[ACM Style]
정윤송, 김준식, and 이동훈. 2018. Privacy-Preserving k-means Clustering of Encrypted Data. Journal of The Korea Institute of Information Security and Cryptology, 28, 6, (2018), 1401-1414. DOI: 10.13089/JKIISC.2018.28.6.1401.