Marco Romanelli

Publication Activity (10 Years)

Years Active: 2018-2024
Publications (10 Years): 27

Top Topics

Shannon Entropy

Machine Learning

Hypothesis Testing

Top Venues

Publications

Animesh Basak Chowdhury, Marco Romanelli, Benjamin Tan, Ramesh Karri, Siddharth Garg
Retrieval-Guided Reinforcement Learning for Boolean Circuit Minimization. ICLR (2024)
Eduardo Dadalto Câmara Gomes, Marco Romanelli, Georg Pichler, Pablo Piantanida
A Data-Driven Measure of Relative Uncertainty for Misclassification Detection. ICLR (2024)
Animesh Basak Chowdhury, Marco Romanelli, Benjamin Tan, Ramesh Karri, Siddharth Garg
Retrieval-Guided Reinforcement Learning for Boolean Circuit Minimization. CoRR (2024)
Federica Granese, Marco Romanelli, Pablo Piantanida
Optimal Zero-Shot Detector for Multi-Armed Attacks. AISTATS (2024)
Georg Pichler, Marco Romanelli, Divya Prakash Manivannan, Prashanth Krishnamurthy, Farshad Khorrami, Siddharth Garg
On the (In)feasibility of ML Backdoor Detection as an Hypothesis Testing Problem. AISTATS (2024)
Federica Granese, Marco Romanelli, Pablo Piantanida
Optimal Zero-Shot Detector for Multi-Armed Attacks. CoRR (2024)
Andrés Altieri, Marco Romanelli, Georg Pichler, Florence Alberge, Pablo Piantanida
Beyond the Norms: Detecting Prediction Errors in Regression Models. CoRR (2024)
Georg Pichler, Marco Romanelli, Divya Prakash Manivannan, Prashanth Krishnamurthy, Farshad Khorrami, Siddharth Garg
On the (In)feasibility of ML Backdoor Detection as an Hypothesis Testing Problem. CoRR (2024)
Saswat Das, Marco Romanelli, Cuong Tran, Zarreen Reza, Bhavya Kailkhura, Ferdinando Fioretto
Low-rank finetuning for LLMs: A fairness perspective. CoRR (2024)
Federica Granese, Marco Romanelli, Siddharth Garg, Pablo Piantanida
A Minimax Approach Against Multi-Armed Adversarial Attacks Detection. CoRR (2023)
Animesh Basak Chowdhury, Marco Romanelli, Benjamin Tan, Ramesh Karri, Siddharth Garg
INVICTUS: Optimizing Boolean Logic Circuit Synthesis via Synergistic Learning and Search. CoRR (2023)
Eduardo Dadalto, Marco Romanelli, Georg Pichler, Pablo Piantanida
A Data-Driven Measure of Relative Uncertainty for Misclassification Detection. CoRR (2023)
Marine Picot, Federica Granese, Guillaume Staerman, Marco Romanelli, Francisco Messina, Pablo Piantanida, Pierre Colombo
A Halfspace-Mass Depth-Based Method for Adversarial Attack Detection. Trans. Mach. Learn. Res. 2023 (2023)
Georg Pichler, Marco Romanelli, Leonardo Rey Vega, Pablo Piantanida
Perfectly Accurate Membership Inference by a Dishonest Central Server in Federated Learning. CoRR (2022)
Federica Granese, Marine Picot, Marco Romanelli, Francisco Messina, Pablo Piantanida
MEAD: A Multi-Armed Approach for Evaluation of Adversarial Examples Detectors. CoRR (2022)
Federica Granese, Marine Picot, Marco Romanelli, Francesco Messina, Pablo Piantanida
MEAD: A Multi-Armed Approach for Evaluation of Adversarial Examples Detectors. ECML/PKDD (3) (2022)
Federica Granese, Marco Romanelli, Daniele Gorla, Catuscia Palamidessi, Pablo Piantanida
DOCTOR: A Simple Method for Detecting Misclassification Errors. NeurIPS (2021)
Federica Granese, Marco Romanelli, Daniele Gorla, Catuscia Palamidessi, Pablo Piantanida
DOCTOR: A Simple Method for Detecting Misclassification Errors. CoRR (2021)
Marco Romanelli, Konstantinos Chatzikokolakis, Catuscia Palamidessi, Pablo Piantanida
Estimating g-Leakage via Machine Learning. CCS (2020)
Catuscia Palamidessi, Marco Romanelli
Modern Applications of Game-Theoretic Principles (Invited Paper). CONCUR (2020)
Moreno Falaschi, Catuscia Palamidessi, Marco Romanelli
Derivation of Constraints from Machine Learning Models and Applications to Security and Privacy. Gabbrielli's Festschrift (2020)
Marco Romanelli, Konstantinos Chatzikokolakis, Catuscia Palamidessi, Pablo Piantanida
Estimating g-Leakage via Machine Learning. CoRR (2020)
Catuscia Palamidessi, Marco Romanelli
Feature selection in machine learning: Rényi min-entropy vs Shannon entropy. CoRR (2020)
Marco Romanelli, Konstantinos Chatzikokolakis, Catuscia Palamidessi
Optimal Obfuscation Mechanisms via Machine Learning. CSF (2020)
Mattia Dalsass, Margherita Bodini, Christophe G. Lambert, Marie-Cécile Mortier, Marco Romanelli, Duccio Medini, Alessandro Muzzi, Alessandro Brozzi
STRAIN: an R package for multi-locus sequence typing from whole genome sequencing data. BMC Bioinform. (9) (2019)
Marco Romanelli, Catuscia Palamidessi, Konstantinos Chatzikokolakis
Generating Optimal Privacy-Protection Mechanisms via Machine Learning. CoRR (2019)
Catuscia Palamidessi, Marco Romanelli
Feature Selection with Rényi Min-Entropy. ANNPR (2018)