Work

On the (Im)Possibility of Estimating Various Notions of Differential Privacy (short paper)

Year: 2023

Type: conference-paper

Abstract: We analyze to what extent final users can infer information about the level of protection of their data when the data obfuscation mechanism is a priori unknown to them (the so-called "black-box" scenario).In particular, we delve into the investigation of two notions of local differential privacy (LDP), namely 𝜀-LDP and Rényi LDP.On one hand, we prove that, without any assumption on the underlying distributions, it is not possible to have an algorithm able to infer the level of data protection with provable guarantees.On the other hand, we demonstrate that, under reasonable assumptions (namely, Lipschitzness of the involved densities on a closed interval), such guarantees exist and can be achieved by a simple histogram-based estimator.

Source: HAL

Authors: Gorla, Daniele, Jalouzot, Louis, Granese, Federica, Palamidessi, Catuscia, Piantanida, Pablo

Institutions: Sapienza University of Rome, École Normale Supérieure de Lyon, École Polytechnique, Université Paris-Saclay, Laboratoire des signaux et systèmes

Language: English

Topic: Privacy-Preserving Technologies in Data

Subfield: Artificial Intelligence

Field: Computer Science

Domain: Physical Sciences

Open Access status: green

OpenAlex ID: W4389909494

FWCI:

Cites:

Cited by:

Related to: 10