Private measures, random walks, and synthetic data

arXiv:2204.09167v2 Announce Type: replace
Abstract: Differential privacy is a mathematical concept that provides an information-theoretic security guarantee. While differential privacy has emerged as a de facto standard for guaranteeing privacy in data sharing, the known mechanisms to achieve it come with some serious limitations. Utility guarantees are usually provided only for a fixed, a priori specified set of queries. Moreover, there are no utility guarantees for more complex - but very common - machine learning tasks such as clustering or …

arxiv concept cs.cr data data sharing differential privacy guarantee information limitations math.pr math.st privacy private random security serious sharing standard stat.th synthetic synthetic data utility