Vol-3881
urn:nbn:de:0074-3881-3

Copyright © 2024 for the individual papers by the papers' authors. Copyright © 2024 for the volume as a collection by its editors. This volume and its papers are published under the Creative Commons License Attribution 4.0 International (CC BY 4.0).

BEWARE 2024
Bias, Risk, Explainability, Ethical AI and the role of Logic and Logic Programming 2024

Proceedings of the 3rd Workshop on Bias, Ethical AI, Explainability and the role of Logic and Logic Programming
co-located with the 23rd International Conference of the Italian Association for Artificial Intelligence (AIxIA 2024)

Bolzano, Italy, November 26, 2024.

Edited by

Greta Coraglia *
Fabio Aurelio D’Asaro
Abeer Dyoub *
Francesca Alessandra Lisi ***
Giuseppe Primiero *

* Department of Philosophy, University of Milan, Italy
** Department of Human Sciences, University of Verona, Italy
*** Computer Science Department, University of Bari, Italy

Table of Contents

Preface
Summary: There were 16 papers submitted for peer-review to this workshop. Out of these, 12 papers were accepted for this volume, 6 as regular papers and 6 as short papers.

Session I: Bias, Fairness and Trust

Prior to Trust: Frequentist and Bayesian Views of Trust in AI (Short Paper) 1
Mattia Petrolo, Ekaterina Kubyshkina, Giuseppe Primiero
Rethinking Bias and Fairness in AI Through the Lens of Gender Studies 6-22
Gabriele Nino, Francesca Alessandra Lisi
Gender Biases in Robots for Education 23-35
Laura Cesaro, Andrea Franceschini, Silvana Badaloni, Emanuele Menegatti, Antonio Rodà

Session II: Ethical Decision Making and Bias Handling in AI-based Systems

Towards Ethical Risk Assessment of Symbiotic AI Systems with Fuzzy Rules 36-49
Abeer Dyoub, Francesca Alessandra Lisi
Towards Efficient Norm-Aware Robots' Decision Making Using Datalog (Short Paper) 50-59
Mahrokh Mirani, Franco Raimondi, Nicolas Troquard
Debiasing Computer Vision Models using Data Augmentation based Adversarial Techniques 59-70
Teerath Kumar, Abhishek Mandal, Susan Leavy, Suzanne Little, Alessandra Mileo, Malika Bendechache,
A Perturbation-based Dataset Evaluation Approach for Fair Classifications (Short Paper) 70-76
Davide Di Pierro, Stefano Ferilli
Bias Amplification Chains in ML-based Systems with an Application to Credit Scoring 77-86
Alessandro G. Buda, Greta Coraglia, Francesco A. Genco, Chiara Manganini, Giuseppe Primiero

Session III: Legal Aspects and Model Inspection

Artificial Intelligence as a Peacebuilding Tool: What is Missing? A Comparative Legal Analysis 87-98
Sveva Ianese
United Nations, Artificial Intelligences and Regulations: Analysis of the General Assembly AI Resolutions and the Final Report of the Advisory Body on AI (Short Paper) 99-106
Ariel Vercelli
A Roadmap from Weights to Wisdom: Inspecting and Extracting Knowledge from Graph Neural Networks (Short Paper) 107-114
Artem Chernobrovkin
Does Content Effect in LLMs Point to Genuine Reasoning? (Short Paper) 115-120
Karthik Prasanna Natarajan

2024-11-28: submitted by Abeer Dyoub, metadata incl. bibliographic data published under Creative Commons CC0
2024-12-22: published on CEUR Workshop Proceedings (CEUR-WS.org, ISSN 1613-0073) |valid HTML5|