RESPONSIBLE AI GOVERNANCE: BALANCING THE GOALS OF BIAS MITIGATION AND PRIVACY PROTECTION THROUGH TRANSPARENCY

Amid increasing societal reliance on artificial intelligence (AI), this thesis begins by establishing a foundational understanding of AI systems, their capabilities, applications, and social implications, before turning to its central focus: the interplay between the goals of debiasing AI systems and safeguarding privacy. While the development and use of AI systems offer significant benefits, they also present serious risks, including data-driven bias that reinforces social inequalities and improper data handling that compromises privacy. Addressing these dual challenges is central to the European Union’s (EU) framework for responsible AI governance. Against this backdrop, the study critically engages with the technical and ethical dimensions of how these pressing concerns intersect. It then examines two key regulatory pillars—the General Data Protection Regulation (GDPR) and the Artificial Intelligence Act (AIA)—recognizing their foundational roles while also exposing regulatory blind spots that warrant greater attention. The analysis highlights the significance of proper data strategies, suggesting the critical role of proportionality, contextual, and evidence-based approaches. The central argument of this thesis is that the EU’s responsible AI governance framework should be rooted in transparent and accountable decision-making, where technical, ethical, and regulatory strategies are coherently aligned. In the quest to balance bias mitigation and privacy protection, the thesis proposes dynamic transparency as both a bridging principle and an internal governance approach. When initiatives are driven by strong internal commitment and reinforced by externally coordinated efforts among relevant actors through diverse transparency-oriented mechanisms, the groundwork is laid for AI systems that are not only innovative but also developed and deployed responsibly.

Grantor dc:publisher

Università degli Studi di Milano

Year dc:date

2026

Author dc:creator

• NAVDARASHVILI, TAMAR

Contributors dc:contributor

• tutor: L. Cominelli ; co-tutor: I. Pellizzone ; coordinator: D. U. Galetta
• T. Navdarashvili
• COMINELLI, LUIGI
• GALETTA, DIANA URANIA

• AI
• responsible governance
• bias mitigation
• privacy protection
• transparency
• Settore GIUR-17/A - Filosofia del diritto

Statement dc:rights

• info:eu-repo/semantics/embargoedAccess
• license:Creative commons
• license uri:http://creativecommons.org/licenses/by-sa/4.0/

Language dc:language

eng

Handle dc:identifier

https://hdl.handle.net/2434/1217956

OAI identifier oai:identifier

oai:air.unimi.it:2434/1217956