Get our free extension to see links to code for papers anywhere online!

Chrome logo  Add to Chrome

Firefox logo Add to Firefox

MEAD: A Multi-Armed Approach for Evaluation of Adversarial Examples Detectors



Federica Granese , Marine Picot , Marco Romanelli , Francisco Messina , Pablo Piantanida

* This paper has been accepted to appear in the Proceedings of the 2022 European Conference on Machine Learning and Data Mining (ECML-PKDD), 19th to the 23rd of September, Grenoble, France 

   Access Paper or Ask Questions

Perfectly Accurate Membership Inference by a Dishonest Central Server in Federated Learning



Georg Pichler , Marco Romanelli , Leonardo Rey Vega , Pablo Piantanida

* 6 pages 

   Access Paper or Ask Questions

DOCTOR: A Simple Method for Detecting Misclassification Errors



Federica Granese , Marco Romanelli , Daniele Gorla , Catuscia Palamidessi , Pablo Piantanida


   Access Paper or Ask Questions

Estimating g-Leakage via Machine Learning



Marco Romanelli , Konstantinos Chatzikokolakis , Catuscia Palamidessi , Pablo Piantanida


   Access Paper or Ask Questions

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



Catuscia Palamidessi , Marco Romanelli

* 16 pages 

   Access Paper or Ask Questions

Generating Optimal Privacy-Protection Mechanisms via Machine Learning



Marco Romanelli , Catuscia Palamidessi , Konstantinos Chatzikokolakis


   Access Paper or Ask Questions