معرفی
Marco Romanelli is a Research Associate at NYU Tandon School of Engineering, Department of Electrical and Computer Engineering, advised by Professor Siddharth Garg. His research focuses on the intersection of information theory, machine learning, privacy, security, and AI safety, with a particular emphasis on information leakage measurement.
- PhD in Computer Science (2020) from École Polytechnique and Inria
- MSc in Computer and Automation Engineering (2017) from Università di Siena
- BSc in Ingegneria Informatica e dell'Informazione (2014) from Università di Siena
His work addresses critical challenges in privacy-preserving machine learning, fairness in AI, and uncertainty quantification, particularly for regression models and out-of-distribution detection. Recent publications explore the feasibility of backdoor detection, low-rank fine-tuning of LLMs, and secure hardware design via reinforcement learning.
Marco’s research has been recognized with a Best Paper Award at colorai 2025. He collaborates with colleagues such as Eduardo, Saswat, Ferdinando, Georg, Pablo, and Animesh. His software contributions are available on GitHub.
