PORTO @ Archivio Istituzionale della Ricerca

How to Make Reproducible Research in Machine Unlearning with ERASURE

Machine unlearning, the process of removing specific data influences from Machine Learning models, is critical for complying with regulations like the GDPR's right to be forgotten and addressing copyright disputes in large models. Despite its rising importance, the field still lacks standardized tools, hindering reproducibility and evaluation. Here, we present, in an extensive way, ERASURE, a unified framework enabling reproducibility by implementing common unlearning techniques, evaluation m...

ERASURE: A Modular and Extensible Framework for Machine Unlearning

Machine Unlearning (MU) is an emerging research area that enables models to selectively forget specific data, a critical requirement for privacy compliance (e.g., GDPR, CCPA) and security. However, the lack of standardized benchmarks makes evaluating and developing unlearning methods difficult. To address this gap, we introduce ERASURE, a benchmarking and development framework designed to systematically assess MU techniques. ERASURE provides a modular, extensible, open-source environmen...

Research on sustainable urban design based on small-scale and Progressive concept

Hydrogen storage system design: case studies for airborne application

Hydrogen represents one of the most promising alternatives to fossil fuels in reaching net-zero emissions targets. In addition, the high energetic content of hydrogen, together with the development of innovative technologies, can be exploited to design aircraft with improved performance. In the present study, the H2 vessel parametric model is described, validated, and applied to two case studies: a regional aircraft (ATR) and an Unmanned Aerial Vehicle (UAV). Results show that increases in th...