A UNIFIED INTERPRETATION OF THE GAUSSIAN MECHANISM FOR DIFFERENTIAL PRIVACY THROUGH THE SENSITIVITY INDEX
Kaissis G, Knolle M, Jungmann F, Ziller A, Usynin D, Rueckert D (2022)
Publication Type: Journal article
Publication year: 2022
Journal
Book Volume: 12
Journal Issue: 1
DOI: 10.29012/jpc.807
Abstract
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.
Involved external institutions
Germany (DE)How to cite
APA:
Kaissis, G., Knolle, M., Jungmann, F., Ziller, A., Usynin, D., & Rueckert, D. (2022). A UNIFIED INTERPRETATION OF THE GAUSSIAN MECHANISM FOR DIFFERENTIAL PRIVACY THROUGH THE SENSITIVITY INDEX. Journal of Privacy and Confidentiality, 12(1). https://doi.org/10.29012/jpc.807
MLA:
Kaissis, Georgios, et al. "A UNIFIED INTERPRETATION OF THE GAUSSIAN MECHANISM FOR DIFFERENTIAL PRIVACY THROUGH THE SENSITIVITY INDEX." Journal of Privacy and Confidentiality 12.1 (2022).
BibTeX: Download