research
∙
03/17/2022
On the Properties of Adversarially-Trained CNNs
Adversarial Training has proved to be an effective training paradigm to ...
share
research
∙
12/23/2021
AcME – Accelerated Model-agnostic Explanations: Fast Whitening of the Machine-Learning Black Box
In the context of human-in-the-loop Machine Learning applications, like ...
research
∙
12/21/2021
Improving Robustness with Image Filtering
Adversarial robustness is one of the most challenging problems in Deep L...
research
∙
05/21/2021
Algorithmic Audit of Italian Car Insurance: Evidence of Unfairness in Access and Pricing
We conduct an audit of pricing algorithms employed by companies in the I...
research
∙
07/21/2020