Privacy-preserving evaluation for support vector clustering

Abstract

The authors proposed a privacy-preserving evaluation algorithm for support vector clustering with a fully homomorphic encryption. The proposed method assigns clustering labels to encrypted test data with an encrypted support function. This method inherits the advantageous properties of support vector clustering, which is naturally inductive to cluster new test data from complex distributions. The authors efficiently implemented the proposed method with elaborate packing of the plaintexts and avoiding non-polynomial operations that are not friendly to homomorphic encryption. These experimental results showed that the proposed model is effective in terms of clustering performance and has robustness against the error that occurs from homomorphic evaluation and approximate operations.