no code implementations • 27 Feb 2024 • Daniele Angioni, Luca Demetrio, Maura Pintor, Luca Oneto, Davide Anguita, Battista Biggio, Fabio Roli
In this work, we show that this problem also affects robustness to adversarial examples, thereby hindering the development of secure model update practices.
no code implementations • NeurIPS 2011 • Luca Oneto, Davide Anguita, Alessandro Ghio, Sandro Ridella
We derive here new generalization bounds, based on Rademacher Complexity theory, for model selection and error estimation of linear (kernel) classifiers, which exploit the availability of unlabeled samples.