Dual Sparseness Constrained Nonnegative Matrix Factorization for Data Privacy and High Accuracy Utility ⋆

In this paper, we propose a data distortion strategy based on dual sparseness constrained Nonnegative Matrix Factorization (NMF). The dual sparseness constrained nonnegative matrix factorization model incorporates attached term constrain and positive symmetric matrix into NMF, which is different from the previous approaches. The goal of our study is data perturbation and we study the distortion level of the algorithm with the standard NMF techniques and its sparse variants. K-means is used to evaluate the data utility of the proposed method. Experimental results indicate that, in comparison with previous published data distortion techniques, the proposed schemes are very promising solution for achieving both data privacy and data utility. At the same time, it provides a feasible method to protect sensitive information and promises higher accuracy for classification.