arXiv:2611.01218v1 Announce Type: new Abstract: Gaussian differential privacy (GDP) and zero-concentrated differential privacy (zCDP) are two competing privacy accounting frameworks, but they share similar minimax lower bounds in various estimation problems. Moreover, it is known that a mechanism satisfying $\mu$-GDP satisfies $(\mu^2/2)$-zCDP, whereas the converse fails to hold at the same calibration.
Optimal Conversion from Zero-Concentrated to Gaussian Differential Privacy
About this summary. This is a short excerpt from the description that arXiv cs.CR published with its article. Cyber Security News did not report or verify the underlying story. Read the original: https://arxiv.org/abs/2611.01218
Source attribution: headline and facts are from arXiv cs.CR (arxiv.org). Summary method: excerpt of the source description. See our source attribution policy.



