A Blockchain-Integrated Divided-Block Sparse Matrix Transformation Differential Privacy Data Publishing Model

Table 2

Effect of traditional Householder transform and sparse matrix transform on the mean square error.

Privacy budget parameters	0.1	0.4	0.7	1	1.3	1.6
Wishart perturbation with Householder transform dimensionality reduction	92432	31585	8246	4329	2054	317
DSMT-DP (with Wishart perturbation and SMT dimensionality reduction)	64972	21426	5373	2324	1508	219