Publications

BibTex format

@article{Kaissis:2022:10.29012/jpc.807,
author = {Kaissis, G and Knolle, M and Jungmann, F and Ziller, A and Usynin, D and Rueckert, D},
doi = {10.29012/jpc.807},
journal = {Journal of Privacy and Confidentiality},
title = {A UNIFIED INTERPRETATION OF THE GAUSSIAN MECHANISM FOR DIFFERENTIAL PRIVACY THROUGH THE SENSITIVITY INDEX},
url = {http://dx.doi.org/10.29012/jpc.807},
volume = {12},
year = {2022}
}

Download

RIS format (EndNote, RefMan)

TY  - JOUR
AB  - The Gaussian mechanism (GM) represents a universally employed tool for achieving differential privacy (DP), and a large body of work has been devoted to its analysis. We argue that the three prevailing interpretations of the GM, namely (ε, δ)-DP, f-DP and Rényi DP can be expressed by using a single parameter ψ, which we term the sensitivity index. ψ uniquely characterises the GM and its properties by encapsulating its two fundamental quantities: the sensitivity of the query and the magnitude of the noise perturbation. With strong links to the ROC curve and the hypothesis-testing interpretation of DP, ψ offers the practitioner a powerful method for interpreting, comparing and communicating the privacy guarantees of Gaussian mechanisms.
AU  - Kaissis,G
AU  - Knolle,M
AU  - Jungmann,F
AU  - Ziller,A
AU  - Usynin,D
AU  - Rueckert,D
DO  - 10.29012/jpc.807
PY  - 2022///
TI  - A UNIFIED INTERPRETATION OF THE GAUSSIAN MECHANISM FOR DIFFERENTIAL PRIVACY THROUGH THE SENSITIVITY INDEX
T2  - Journal of Privacy and Confidentiality
UR  - http://dx.doi.org/10.29012/jpc.807
VL  - 12
ER  -

Download

ProfessorDanielRueckert

Contact

Location

Summary

Citation

BibTex format

RIS format (EndNote, RefMan)