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 distri- butions, 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, Lipschitz- ness of the involved densities on a closed interval), such guarantees exist and can be achieved by a simple histogram-based estimator.
On the (Im)Possibility of Estimating Various Notions of Differential Privacy / Gorla, Daniele; Jalouzot, Louis; Granese, Federica; Palamidessi, Catuscia; Piantanida, Pablo. - 3587:(2023), pp. 219-224. (Intervento presentato al convegno 24th Italian Conference on Theoretical Computer Science tenutosi a Palermo (Italiy)).
On the (Im)Possibility of Estimating Various Notions of Differential Privacy
Daniele Gorla;Federica Granese;
2023
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 distri- butions, 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, Lipschitz- ness of the involved densities on a closed interval), such guarantees exist and can be achieved by a simple histogram-based estimator.I documenti in IRIS sono protetti da copyright e tutti i diritti sono riservati, salvo diversa indicazione.