Giandomenico Cornacchia

Giandomenico is a Research Scientist in the AI Security and Privacy team at IBM Research Europe, Dublin!

Before joining IBM, he received his Bachelor's and Master's degrees in Management Engineering and his Ph.D. in Computer Engineering at the Polytechnic University of Bari. His doctoral research project focused on developing novel auditing methodologies for assessing the ethical implications of AI technologies under the lens and guidelines of the EU AI Act. Specifically, he worked on developing new methods for assessing Fairness and Discrimination in Machine Learning models through the use of Counterfactual Reasoning. During his doctoral studies, Giandomenico authored more than 10 peer-reviewed publications.

Between 2021 and 2023, he worked on various research projects as a Research Associate at EY, a Research Fellow, and a Teaching Assistant at the Polytechnic University of Bari. From May 2023 to October 2023, he interned at IBM Research, working on the privacy of foundation models for code generation.

Recently, his research primarily focuses on the Robustness, Privacy, Safety, and Trustworthiness of AI foundation models, including Large Language Models (LLMs).