In the field of Explainable Artificial Intelligence (XAI), counterfactua...
Most works on the fairness of machine learning systems focus on the blin...
In the field of eXplainable Artificial Intelligence (XAI), post-hoc
inte...
Explainability is becoming an important requirement for organizations th...
This paper analyses the fundamental ingredients behind surrogate explana...
Local surrogate approaches for explaining machine learning model predict...
A multitude of classifiers can be trained on the same data to achieve si...
Security of machine learning models is a concern as they may face advers...
Post-hoc interpretability approaches have been proven to be powerful too...
Counterfactual post-hoc interpretability approaches have been proven to ...
Machine learning models are increasingly used in the industry to make
de...
Local surrogate models, to approximate the local decision boundary of a
...
In the context of post-hoc interpretability, this paper addresses the ta...