About Me

I am a PhD candidate at the CISPA Helmholtz Center for Information Security, and advised by Franziska Boenisch and Adam Dziedzic. My research focuses on privacy and security for machine learning.

Before joining CISPA, I completed an MSc in Data Science at ETH Zurich, where I worked with Florian Tramèr. I previously earned a BSc in Engineering of Computing Systems from Politecnico di Milano.

🔥 News

2026.03

🎉 Benchmarking Empirical Privacy Protection for Adaptations of Large Language Models

Accepted to ICLR 2026 (Oral).

2026.03

🎉 Natural Identifiers for Privacy and Data Audits in Large Language Models

Accepted to ICLR 2026.

📝 Selected Publications

* indicates equal contribution. Full list of publications

Representative image for Benchmarking Empirical Privacy Protection for Adaptations of Large Language Models

Benchmarking Empirical Privacy Protection for Adaptations of Large Language Models

Bartlomiej Marek*, Lorenzo Rossi*, Vincent Hanke, Xun Wang, Michael Backes, Franziska Boenisch, Adam Dziedzic

Representative image for Natural Identifiers for Privacy and Data Audits in Large Language Models

Natural Identifiers for Privacy and Data Audits in Large Language Models

Lorenzo Rossi, Bartlomiej Marek, Franziska Boenisch, Adam Dziedzic

Representative figure for Membership Inference Attacks on Sequence Models

Membership Inference Attacks on Sequence Models

Lorenzo Rossi, Michael Aerni, Jie Zhang, Florian Tramer

🤝 Service

Conference Reviewing

AAAI 2026 and ICML 2026.

Workshop Reviewing

AAAI 2026 Workshop on AI Governance, ICLR 2026 Workshop on DATA-FM, ICLR 2026 Workshop on SPOT, ICML 2025 Workshop on Trustworthy AI, and MemFM.