Marco Romanelli

According to our database, Marco Romanelli authored at least 23 papers between 2018 and 2024.

Collaborative distances:

• Dijkstra number of four.
• Erdős number of three.

2024

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

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

IEEE Trans. Dependable Secur. Comput., 2024

Low-rank finetuning for LLMs: A fairness perspective.

Saswat Das, Marco Romanelli, Cuong Tran, Zarreen Reza, Bhavya Kailkhura, Ferdinando Fioretto

CoRR, 2024

Disparate Impact on Group Accuracy of Linearization for Private Inference.

Saswat Das, Marco Romanelli, Ferdinando Fioretto

Proceedings of the Forty-first International Conference on Machine Learning, 2024

Beyond the Norms: Detecting Prediction Errors in Regression Models.

Andrés Altieri, Marco Romanelli, Georg Pichler, Florence Alberge, Pablo Piantanida

Proceedings of the Forty-first International Conference on Machine Learning, 2024

A Data-Driven Measure of Relative Uncertainty for Misclassification Detection.

Eduardo Dadalto Câmara Gomes, Marco Romanelli, Georg Pichler, Pablo Piantanida

Proceedings of the Twelfth International Conference on Learning Representations, 2024

Retrieval-Guided Reinforcement Learning for Boolean Circuit Minimization.

Animesh Basak Chowdhury, Marco Romanelli, Benjamin Tan, Ramesh Karri, Siddharth Garg

Proceedings of the Twelfth International Conference on Learning Representations, 2024

On the (In)feasibility of ML Backdoor Detection as an Hypothesis Testing Problem.

Georg Pichler, Marco Romanelli, Divya Prakash Manivannan, Prashanth Krishnamurthy, Farshad Khorrami, Siddharth Garg

Proceedings of the International Conference on Artificial Intelligence and Statistics, 2024

Optimal Zero-Shot Detector for Multi-Armed Attacks.

Federica Granese, Marco Romanelli, Pablo Piantanida

Proceedings of the International Conference on Artificial Intelligence and Statistics, 2024

2023

A Halfspace-Mass Depth-Based Method for Adversarial Attack Detection.

Marine Picot, Federica Granese, Guillaume Staerman, Marco Romanelli, Francisco Messina, Pablo Piantanida, Pierre Colombo

Trans. Mach. Learn. Res., 2023

INVICTUS: Optimizing Boolean Logic Circuit Synthesis via Synergistic Learning and Search.

Animesh Basak Chowdhury, Marco Romanelli, Benjamin Tan, Ramesh Karri, Siddharth Garg

CoRR, 2023

A Minimax Approach Against Multi-Armed Adversarial Attacks Detection.

Federica Granese, Marco Romanelli, Siddharth Garg, Pablo Piantanida

CoRR, 2023

2022

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

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

CoRR, 2022

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

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

Proceedings of the Machine Learning and Knowledge Discovery in Databases, 2022

2021

DOCTOR: A Simple Method for Detecting Misclassification Errors.

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

Proceedings of the Advances in Neural Information Processing Systems 34: Annual Conference on Neural Information Processing Systems 2021, 2021

2020

Machine learning methods for privacy protection : leakage measurement and mechanisms design. (Méthodes d'apprentissage machine pour la protection de la vie privée : mesure de leakage et design des mécanismes).

Marco Romanelli

PhD thesis, 2020

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

Catuscia Palamidessi, Marco Romanelli

CoRR, 2020

Optimal Obfuscation Mechanisms via Machine Learning.

Marco Romanelli, Konstantinos Chatzikokolakis, Catuscia Palamidessi

Proceedings of the 33rd IEEE Computer Security Foundations Symposium, 2020

Modern Applications of Game-Theoretic Principles (Invited Paper).

Catuscia Palamidessi, Marco Romanelli

Proceedings of the 31st International Conference on Concurrency Theory, 2020

Estimating g-Leakage via Machine Learning.

Marco Romanelli, Konstantinos Chatzikokolakis, Catuscia Palamidessi, Pablo Piantanida

Proceedings of the CCS '20: 2020 ACM SIGSAC Conference on Computer and Communications Security, 2020

Derivation of Constraints from Machine Learning Models and Applications to Security and Privacy.

Moreno Falaschi, Catuscia Palamidessi, Marco Romanelli

Proceedings of the Recent Developments in the Design and Implementation of Programming Languages, 2020

2019

Generating Optimal Privacy-Protection Mechanisms via Machine Learning.

Marco Romanelli, Catuscia Palamidessi, Konstantinos Chatzikokolakis

CoRR, 2019

STRAIN: an R package for multi-locus sequence typing from whole genome sequencing data.

Mattia Dalsass, Margherita Bodini, Christophe G. Lambert, Marie-Cécile Mortier, Marco Romanelli, Duccio Medini, Alessandro Muzzi, Alessandro Brozzi

BMC Bioinform., 2019

2018

Feature Selection with Rényi Min-Entropy.

Catuscia Palamidessi, Marco Romanelli

Proceedings of the Artificial Neural Networks in Pattern Recognition, 2018