A common practice of ML systems development concerns the training of the same model under different data sets, and the use of the same (training and test) sets for different learning models. The first case is a desirable practice for identifying high quality and unbiased training...

In this article we propose an extension to the typed natural deduction calculus TNDPQ to model verification of counterfactual fairness in probabilistic classifiers. This is obtained formulating specific structural conditions for causal labels and checking that evaluation is robust...

In this article we propose an extension to the typed natural deduction calculus TNDPQ to model verification of individual fairness and intersectionality in probabilistic classifiers. Their interpretation is obtained by formulating specific conditions for the application of the...

In the present work, we develop a novel information-theoretic and logic-based approach to data bias in Machine Learning predictions and show its relevance in the specific context of fairness evaluation. We frame predictions made on biased data as Ulam games, which formalise key...

Negli ultimi anni, il crescente uso dell’intelligenza artificiale (IA) in diversi settori ha portato enormi cambiamenti sociali, culturali, e tecnologici, specialmente laddove integrata all’interno di processi decisionali. In particolare il credit scoring, ovvero la stima...

The widespread emergence of phenomena of bias is certainly among the most adverse impacts of new data-intensive sciences and technologies. The causes of such undesirable behaviours must be traced back to data themselves, as well as to certain design choices of machine learning...

Machine Learning (ML) systems, whether predictive or generative, not only reproduce biases and stereotypes but, even more worryingly, amplify them. Strategies for bias detection and mitigation typically focus on either ex post or ex ante approaches, but are always limited to two...

We present a method for quantitative, in-depth analyses of fairness issues in AI systems with an application to credit scoring. To this aim we use BRIO, a tool for the evaluation of AI systems with respect to social unfairness and, more in general, ethically undesirable behaviours....

We present a tool for the detection of biased behaviours in AI systems. Using a specific probability-based algorithm, we provide the means to compare the action of the user’s algorithm of choice on a specific feature that they deem “sensible” with respect to fixed classes and to a...

In this paper we present the probabilistic typed natural deduction calculus TPTND, designed to reason about and derive trustworthiness properties of probabilistic computational processes, like those underlying current AI applications. Derivability in TPTND is interpreted as the...