Ethics of AI 2024/2025

  A Hybrid AI System for Adoption Eligibility Assessment with Explainable Feedback — Filippo Teodorani  •  Diego Rossi

  AEQUITAS : Bias free AI assisted recruiting system — Alessandro Tutone  •  Alberto Genovese

  Bias Mitigation in AI Models for Cardiovascular Diseases Prediction — Giorgia Castelli  •  Alice Fratini  •  Madalina Ionela Mone

  Bias in Law School Admissions: Analysis and Mitigation Using Machine Learning — Federico Marchi  •  Christina Baytcheva  •  Anna Di Iulio

  Ensuring Trustworthy Medical AI: Enhancing Robustness and Ethical Integrity of Image Classifiers Against Adversarial Attacks — Matteo Fasulo  •  Luca Babboni  •  Maksim Omelchenko

  Ethical Simulation of Urban Mobility in Bologna’s Digital Twin — Fatemeh Izadinejad  •  Ali Loloeejahromi  •  Hamidreza Bahmanyar

  Ethically Aligned Reward Models: A Language Model Post-Training Framework — Nicolas Cridlig  •  Marco Sangiorgi  •  Andrea Fossa

  Evaluating the Impact of Alignment via DPO on Performance and Harmfulness in LLMs — Abylay Turekhassim

  Evaluation of Privacy Preservation Capabilities through Synthetic Data on Multiple Datasets — Mattia Buzzoni  •  Riccardo Romeo

  Exploit, Defend, and Detect Adversarial Attacks on Image-Based AI Systems: An Ethical Perspective — Mattia Gualandi  •  Presepi Alex  •  Sciarrillo Alessandro

  Fairness in AutoML — Tara Sabooni  •  Yasaman Samadzadeh

  Fairness in Multilingual Sentiment Analysis using DistilBERT — Paul Clotan  •  Valeria Izvoreanu  •  Antonio Gravina

  Fairness-Aware Deep Learning for Early Detection of Autism Spectrum Disorder — Tannaz Masoudian

  Fairness-Aware Static Task Assignment: Toward Ethical Resource Allocation in Multi-Agent Systems — Abdullah Naveed  •  Nadia Farokhpay

  Kernel-Based HGR in Fairness: a case study — Giorgio Adragna  •  Marcello Mancino

  Mitigating Social Bias in LLMs via Multi-Agent Collaboration and Reflective Reasoning — Hesam Sheikh Hassani  •  Mehregan Nazarmohsenifakori  •  Safoura Banihashemi

  Reasoning in LLMs — Alessandro Gentili

  Responsibility in autonomous vehicle accidents : An ethical and legal challenge — Nicolas Chauvet

  Robustness of LLMs — Carlo Merola  •  Jaspinder Singh  •  Othmane Dardouri

  School performance prediction: Ensuring fairness for disadvantaged students — Davide Cremonini  •  Gabriele Nanni

  Smile̸ = Happy: Auditing Emotion Recognition Systems for Bias Against Neurodiverse Individuals — Luwam Major Kefali  •  Hassen Said Ali  •  Hilina Fissha Woreta

  Sustainable City via Trustworthy Digital Twin: a Use Case — Christian Di Buò  •  Simone Reale

  A Comparative Study of Pre-defined and Automatically Discovered Concepts for Interpretability — Valerio Costa  •  Luca Domeniconi

  A Transparent and Fair AI Tool for Candidate Screening with Simulated Human Oversight — Tommaso Perniola  •  Armando Renzullo  •  Cosimo Russo

  Deepfake Video Detection: A Comparative Study — Roberto Giordano  •  Alessio Pittiglio

  Detecting Subjective Bias in Text Using the Wiki Neutrality Corpus — Bahar Hamzehei  •  Taleb Zarhesh

  Detecting and Mitigating Bias in AI-Powered Loan Approval Systems — Eleasar Erz

  Enhancing Explainability in Transformer Models for Detecting Sexism on Twitter — Tancredi Bosi  •  Francesco Farneti  •  Giovanni Grotto

  Exploring Natural Example-Based Local and Global Explainability Across Different Data Types — Claudia Maiolino  •  Tian Cheng Xia

  Fairness Consideration in Digital Twin — Francesco Cavaleri  •  Giacomo Piergentili

  Fairness in EEG-Based Depression Detection — Annisaa Fitri Nurfirdausi

  Formal Safety Assessment of Neural Networks under Adversarial Attacks — Mauro Dore  •  Gian Mario Marongiu  •  Riccardo Murgia

  Investigating Bias in Generative Text-to-Image AI Models — Davide Crociati  •  Davide Sonno

  Mitigating LLM Social Bias by Assessing and Filtering Reasoning Steps with a Multi-Judge Pipeline — Fatemehzahra Ghafari Ghomi  •  Shafagh Rastegari  •  Habib Kazemi

  Predictive Modeling on Real Hiring Data: Exploring Salary Stereotypes and Bias Mitigation — Lyudmil Stamenov

  Profiling Bias in LLMs, LMMs, and LRMs. An Ethical and Legal Framework for the Inclusion of Neurodivergent Users. A Case Study of ChatGPT. — Elisabet Bolarín-Miró

  Robustness in Counterfactual Explanations Generation using LLMs — Chang Sun  •  Xiaofeng Zhang

  The Use of AI in Criminal Justice: Bias and Accountability — Laura Lucchiari

  Toward Trustworthy Diagnosis: Model Comparison and XAI-Guided Ensembling on the CheXpert Dataset — Eugenio De Luca

  Towards Ethical AI in Healthcare: Enhancing Interpretability in ECG Classification through Physician-Guided Knowledge Distillation — Zijun Sun  •  Enze Ge  •  Ruixin Li

  Visual Stereotypes and Language Generation: A Comparative Bias Study of MLLMs — Erfan Samieyan Sahneh  •  Jana Nikolovska