| KEYWORD |
Auditing online software systems for bias
keywords AI AUDIT, AI ETHICS, ARTIFICIAL INTELLINGENCE, DATA SCIENCE, DIGITAL SERVICES, RESPONSIBLE AI, SOFTWARE ENGINEERING
Reference persons ANTONIO VETRO'
Research Groups DAUIN - GR-16 - SOFTWARE ENGINEERING GROUP - SOFTENG, DAUIN - GR-22 - Nexa Center for Internet & Society - NEXA
Thesis type RESEARCH / EXPERIMENTAL, RESEARCH, INNOVATIVE
Description 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.
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
Required skills 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.
Notes 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
Deadline 30/11/2023
PROPONI LA TUA CANDIDATURA