PORTALE DELLA DIDATTICA

Ricerca CERCA
  KEYWORD

DAUIN - GR-16 - SOFTWARE ENGINEERING GROUP - SOFTENG

Developing experimental testing methods and tools for auditing online software systems for bias and discrimination

Parole chiave AI AUDIT, AI ETHICS, ARTIFICIAL INTELLIGENCE, DATA SCIENCE, DIGITAL SERVICES, EXPERIMENTAL TESTING, RESPONSIBLE AI, SOFTWARE ENGINEERING

Riferimenti RICCARDO COPPOLA, ANTONIO VETRO'

Gruppi di ricerca DAUIN - GR-16 - SOFTWARE ENGINEERING GROUP - SOFTENG, DAUIN - GR-22 - Nexa Center for Internet & Society - NEXA

Tipo tesi EXPERIMENTAL, RESEARCH, SPERIMENTALE APPLICATA

Descrizione CONTEXT
There is a growing concern about the issue of bias in online systems. Institutions require higher accountability and transparency of platforms. However, as these software systems became increasingly complex and interconnected, understanding whether they systematically (dis)advantage certain categories of people became extremely difficult. This thesis proposal aims at researching and developing novel and scalable techniques and tools for performing black-box bias audits of online software systems, leveraging existing technologies for end to end systems (e.g., Selenium)

THESIS OBJECTIVES

The thesis research has the following three objectives.

1. Collect and organize existing tools for testing/auditing online software systems (e.g., insurance, online advertising, etc.).
2. Collect and organize metrics and indicators for assessing discrimination.
3. Quantitative analysis of bias in selected existing online software systems

Conoscenze richieste Good programming skills and basic knowledge of common data analytics tools and techniques. Basic knowledge of the working mechanisms of web applications. Curiosity. Grade point average equal to or higher than 26 can be a criterion for selection of candidate.

Note When sending your application, we kindly ask you to attach the following information:

- list of exams taken in you master degree, with grades and grade point average
- a résumé or equivalent (e.g., linkedin profile), if you already have one
- by when you aim to graduate and an estimate of the time you can devote to the thesis in a typical week


Scadenza validita proposta 20/03/2025      PROPONI LA TUA CANDIDATURA




© Politecnico di Torino
Corso Duca degli Abruzzi, 24 - 10129 Torino, ITALY
Contatti