activity
20192026
most citedPerfectly Accurate Membership Inference by a Dishonest Central Server in Federated Learning

15 citations · 28 across the 11 of their papers we have counts for

collaborators
Showing 2020Show all

2 papers · 1 filter

cs.CR2020

Estimating g-Leakage via Machine Learning

Marco Romanelli, Konstantinos Chatzikokolakis, Catuscia Palamidessi +1

This paper considers the problem of estimating the information leakage of a system in the black-box scenario. It is assumed that the system's internals are unknown to the learner,…

cs.LG2020★ 2 cited

Feature selection in machine learning: Rényi min-entropy vs Shannon entropy

Catuscia Palamidessi, Marco Romanelli

Feature selection, in the context of machine learning, is the process of separating the highly predictive feature from those that might be irrelevant or redundant. Information theo…