Marcello Pelillo

collaborators

3 papers

cs.AI2026

Scientific Explanations in Health Sciences: Causality, Trust, and Epistemic Adequacy

Martina Mattioli, Marcello Pelillo

Medical Artificial Intelligence (AI) is widely expected to transform clinical practice, yet the decision-making processes of many Machine Learning (ML) models remain opaque. Explai…

cs.AI2025

Onto-Epistemological Analysis of AI Explanations

Martina Mattioli, Eike Petersen, Aasa Feragen +2

Artificial intelligence (AI) is being applied in almost every field. At the same time, the currently dominant deep learning methods are fundamentally black-box systems that lack ex…

cs.LG2025

$I ¨ $ -zero: Gradient-based Optimization of $ℓ_{0}$ -norm Adversarial Examples

Antonio Emanuele CinÃ, Francesco Villani, Maura Pintor +3

Evaluating the adversarial robustness of deep networks to gradient-based attacks is challenging. While most attacks consider $ℓ_{2}$ - and $ℓ_{\infty}$ -norm constraints to craft i…

Scientific Explanations in Health Sciences: Causality, Trust, and Epistemic Adequacy

Onto-Epistemological Analysis of AI Explanations

I¨-zero: Gradient-based Optimization of ℓ0​-norm Adversarial Examples

$I ¨ $ -zero: Gradient-based Optimization of $ℓ_{0}$ -norm Adversarial Examples