Romanelli, Marco

12 publications

UAI 2025 Optimal Zero-Shot Regret Minimization for Selective Classification with Out-of-Distribution Detection Eduardo Dadalto Câmara Gomes, Marco Romanelli
ICLR 2024 A Data-Driven Measure of Relative Uncertainty for Misclassification Detection Eduardo Dadalto Câmara Gomes, Marco Romanelli, Georg Pichler, Pablo Piantanida
ICML 2024 Beyond the Norms: Detecting Prediction Errors in Regression Models Andres Altieri, Marco Romanelli, Georg Pichler, Florence Alberge, Pablo Piantanida
ICML 2024 Disparate Impact on Group Accuracy of Linearization for Private Inference Saswat Das, Marco Romanelli, Ferdinando Fioretto
AISTATS 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
AISTATS 2024 Optimal Zero-Shot Detector for Multi-Armed Attacks Federica Granese, Marco Romanelli, Pablo Piantanida
ICLR 2024 Retrieval-Guided Reinforcement Learning for Boolean Circuit Minimization Animesh Basak Chowdhury, Marco Romanelli, Benjamin Tan, Ramesh Karri, Siddharth Garg
NeurIPSW 2023 A Data-Driven Measure of Relative Uncertainty for Misclassification Detection Eduardo Dadalto Câmara Gomes, Marco Romanelli, Georg Pichler, Pablo Piantanida
TMLR 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
NeurIPSW 2023 On the Limitation of Backdoor Detection Methods Georg Pichler, Marco Romanelli, Divya Prakash Manivannan, Prashanth Krishnamurthy, Farshad Khorrami, Siddharth Garg
ECML-PKDD 2022 MEAD: A Multi-Armed Approach for Evaluation of Adversarial Examples Detectors Federica Granese, Marine Picot, Marco Romanelli, Francesco Messina, Pablo Piantanida
NeurIPS 2021 DOCTOR: A Simple Method for Detecting Misclassification Errors Federica Granese, Marco Romanelli, Daniele Gorla, Catuscia Palamidessi, Pablo Piantanida