Ethics of AI 2023/2024

Main

Projects

35 completed projects

bricks

Achieving Fairness without Demographic Information — Alessandro Pasi • Matteo Belletti • Razvan Ciprian Stricescu

bricks

Adversarial Attacks on Time Series Models: A Systematic Literature Review — Davide Bombardi

bricks

Analysis of Explainability ML Techinques against Adversarial Models — Nicola Palli • Terzi Angelo

bricks

Analyzing and Addressing Bias in Face Recognition Using InsightFace Embeddings — Gabriele Fossi

bricks

Automatic Skin Disease Prediction: A Review — Ilenia Carboni

bricks

Bias Mitigation in Face Recognition Models — Matteo Fusconi • Guglielmo Biagini

bricks

Breaking and Fixing: A Study on Neural Network Vulnerabilities and Robustness in the medical field — Alessandro Folloni • Daniele Napolitano • Marco Solime

bricks

Comparative Analysis of Explainability Techniques for Non-linear Models — Alessio Conti

bricks

Comparing Different Models’ Reliance on Prohibited Features in the Adult Census Income — Daniele Baiocco

bricks

Comparison of performance & explainability for Symbolic and Sub-symbolic methods — Alberto Luise

bricks

Defense Algorithms Against A Fast Gradient Sign Method Attack — Oğuz Kağan Koçak • Clara Nunes

bricks

Developing a Fairness Auditing Tool for Income Prediction Models — Mahmut Kaan Molla • Farhad Bayrami

bricks

Developing and Analyzing Fairness in Algorithmic Policing — Thomas Guizzetti

bricks

Evaluating AI Models with the ETHICS Dataset for Ethical Alignment — Gianluca Di Mauro • Leonardo Monti

bricks

Evaluation of Hiring Bias in Large Language Models — Francesco Pivi • Kilian Tiziano Le Creurer

bricks

Explainability of Large Language Models (LLMs) for Anemia Diagnosis — Elisa Castagnari

bricks

Explaining Convolutional Neural Networks: A Literature Overview and Implementation of Explainability Methods — Maxence Murat • Parsa Mastouri Kashani • Sadeghi Khiabanian

bricks

Exploring Toxic and Hate Bias in Large Language Models — Álvaro Esteban Muñoz

bricks

Fairness in Football Player Transfer Value Prediction — Franciszek Wysocki • Gabriel Meira

bricks

Fairness in Recidivism Detection Using Autoencoders and Gaussian Mixture Models — Luca Trambaiollo • Davide Capacchione

bricks

Fairness in Skin disease prediction — Giorgia Pavani • Livia Del Gaudio

bricks

Fairness of predictive policing as a dynamic environment — Edoardo Merli

bricks

Fortifying Medical Diagnosis: Federated Learning Augmented by Blockchain for Enhanced Privacy, Security, and Robustness — Lorenzo Cassano • Jacopo D’Abramo

bricks

GAUNTLET: An Explainable Model for Detecting AI-Generated Images — Angelo Galavotti • Lorenzo Galfano

bricks

Identifying and Mitigating Biases in Recruitment — Mattia Maranzana

bricks

Machine Ethics: approaches and architectures — Elisa Venturoli

bricks

Measuring fairness in automatic skin disease diagnosis with a convolutional neural network — Chiara Bellatreccia

bricks

Prompting Techniques for Gender Equity in Open-Source LLMs — Andrea Zecca • Samuele Marro • Stefano Colamonaco

bricks

Study, Design, and Implement the Knowledge-aware Object Detection Symbolic Knowledge Injection Algorithm — Pelinsu Acar • Rubin Carkaxhia • Calin Diaconu

bricks

Study, design, and implement the [Lyrics] symbolic knowledge injection algorithm — alessio pellegrino

bricks

To encode or not to encode? Explainable approaches for Emotion and Trigger detection on MELD — Umberto Carlucci • Giuseppe Carrino • Matteo Vannucchi

bricks

Transparency and Fairness in Arrival Prediction — fatemeh bozorgi • Reza Shatery • Kankana Gosh

bricks

Unmasking Bias in AI-Driven CV Screening: Evaluating Prompt Engineering Techniques to Enhance Fairness in GPT-4o Decision-Making — Giacomo Gaiani • Salvatore Guarrera • Riccardo Monaco

bricks

Unveiling Political Bias in Artificial Intelligence: A Systematic Literature Review — Giacomo Caroli • Luca Mongiello

bricks

User Persona for LLMs’ bias evaluation — Luca De Dominicis • Marco Lorenzo Damiani Ferretti • Marco Panarelli

11 ongoing projects

bricks

Assessing Bias in Multi-Modal Models: A Study of CLIP on Gender and Skin Tone — Torzi Luca

bricks

Bias Analysis and Ethical Considerations in ML Models for Healthcare — Paolo De Angelis • Francesco Pigliapoco

bricks

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

bricks

Bias mitigation in automated loan eligibility process — Chiara Angileri • Niccol`o Marzi • Shola Oshodi

bricks

Classification of Hand Movements Using DNN, LSTM, and SNN: A Comparative Study — Kashaf Ad Dooja

bricks

Fairness in Recruitment Decisions Algorithms — Riccardo Marvasi • Edoardo Saturno • Lorenzo Balzani

bricks

Fairness in diabetes prediction dataset — Arianna Albertazzi • Lucia Gasperini

bricks

Framework for Symbolic Rules Constraints in Neural Networks — Silje Eriksen

bricks

LIME vs SHAP Comparing ML explanation techniques — Andrea Terenziani

bricks

On the Fairness capability of CatBoost — Edoardo Fusa • Angelo Quarta

bricks

Study, design, and implement the GRAM symbolic knowledge injection algorithm — Davide Freddi • Davide Gardenal