Metric geometry of the privacy-utility tradeoff

arXiv:2405.00329v1 Announce Type: new
Abstract: Synthetic data are an attractive concept to enable privacy in data sharing. A fundamental question is how similar the privacy-preserving synthetic data are compared to the true data. Using metric privacy, an effective generalization of differential privacy beyond the discrete setting, we raise the problem of characterizing the optimal privacy-accuracy tradeoff by the metric geometry of the underlying space. We provide a partial solution to this problem in terms of the "entropic scale", a quantity …

arxiv beyond concept cs.cr cs.ds data data sharing differential privacy enable geometry math.pr metric privacy problem question sharing synthetic synthetic data utility