Locally Private Representation Learning for Responsible Artificial Intelligence
Learning locally private representations for responsible artificial intelligence.
Projects
Selected research projects and collaborations. Additional details are available in my CV.
Current Projects
Responsible AI: Design, Regulation, and Conformity (RAIDAC+)
Building accountable and compliant AI systems by bridging legal, regulatory, and technical dimensions of Responsible AI.
Aligning Privacy, Utility, and Fairness for Responsible AI (AI-PULSE)
Studying fundamental trade-offs between privacy, fairness, and machine learning performance; designing new methods to enforce all three simultaneously.
Algorithmic Auditing of Privacy and Fairness (AUDIT-PAIR)
Cross-continent collaboration on tools and methods for auditing AI systems under privacy and fairness constraints.
Past Projects
Exploring the Interplay of Differential Privacy and Fairness in ML
Empirical and theoretical analysis of fairness–privacy interaction in real-world ML scenarios.