Tight Differential Privacy for Discrete-Valued Mechanisms and for the Subsampled Gaussian Mechanism Using FFT

Antti Koskela*, Joonas Jälkö, Lukas Prediger, Antti Honkela

*Tämän työn vastaava kirjoittaja

Tutkimustuotos: Artikkeli kirjassa/konferenssijulkaisussaConference article in proceedingsScientificvertaisarvioitu

30 Lataukset (Pure)

Abstrakti

We propose a numerical accountant for evaluating the tight (ε,δ)-privacy loss for algorithms with discrete one dimensional output. The method is based on the privacy loss distribution formalism and it uses the recently introduced Fast Fourier Transform based accounting technique. We carry out a complete error analysis of the method in terms of moment bounds of the privacy loss distribution which leads to rigorous lower and upper bounds for the true (ε,δ)-values. As an application we give a novel approach to accurate privacy accounting of the subsampled Gaussian mechanism. This completes the previously proposed analysis by giving a strict lower and upper bounds for the (ε,δ)-values. We also demonstrate the performance of the accountant on the binomial mechanism and show that our approach allows decreasing noise variance up to 75 percent at equal privacy compared to existing bounds in the literature. We also illustrate how to compute tight bounds for the exponential mecha nism applied to counting queries.
AlkuperäiskieliEnglanti
OtsikkoProceedings of The 24th International Conference on Artificial Intelligence and Statistics
ToimittajatA Banerjee, K Fukumizu
KustantajaJMLR
Sivumäärä10
TilaJulkaistu - 2021
OKM-julkaisutyyppiA4 Artikkeli konferenssijulkaisussa
TapahtumaInternational Conference on Artificial Intelligence and Statistics - Virtual, Online
Kesto: 13 huhtik. 202115 huhtik. 2021
Konferenssinumero: 24

Julkaisusarja

NimiProceedings of Machine Learning Research
KustantajaPMLR
Vuosikerta130
ISSN (elektroninen)2640-3498

Conference

ConferenceInternational Conference on Artificial Intelligence and Statistics
LyhennettäAISTATS
KaupunkiVirtual, Online
Ajanjakso13/04/202115/04/2021

Sormenjälki

Sukella tutkimusaiheisiin 'Tight Differential Privacy for Discrete-Valued Mechanisms and for the Subsampled Gaussian Mechanism Using FFT'. Ne muodostavat yhdessä ainutlaatuisen sormenjäljen.

Siteeraa tätä