30 citations · 54 across the 11 of their papers we have counts for
Showing 2023Show all
2 papers · 1 filter
cs.LG2023
Ensembling Uncertainty Measures to Improve Safety of Black-Box Classifiers
Tommaso Zoppi, Andrea Ceccarelli, Andrea Bondavalli
Machine Learning (ML) algorithms that perform classification may predict the wrong class, experiencing misclassifications. It is well-known that misclassifications may have cascadi…
cs.LG2023★ 1 cited
On the Efficacy of Metrics to Describe Adversarial Attacks
Tommaso Puccetti, Tommaso Zoppi, Andrea Ceccarelli
Adversarial defenses are naturally evaluated on their ability to tolerate adversarial attacks. To test defenses, diverse adversarial attacks are crafted, that are usually described…