École Polytechnique Fédérale de Lausanne
Stanford University
Nicolas PapernotResearch Scientist · Google DeepMindResearcher↗
Researcher · Academic
Florian Tramèr
ETH ZürichAssistant Professor of Computer Science
Google DeepMindResearch Scientist
Tramèr helped establish model stealing as an AI security threat, showing how attackers can copy a model by querying it.[1] That work won a 2026 USENIX Security Test of Time Award.[2] He now probes language models and AI agents for weaknesses that expose private data or let malicious instructions hijack their behavior.
Career & education
Current rolesETH Zürich2022-presentAssistant Professor of Computer ScienceGoogle DeepMind2026-presentResearch Scientist
ETH Zürich2022-presentGoogle DeepMind2026-presentPreviously
Google Brain2021-2022Visiting Faculty
Google Brain2021-2022Work and education history is primarily focused on AI-relevant roles and may not be comprehensive.
Citation Trend
Total citations to scholarly work, including research papers, technical reports, books and theses, as recorded by Google Scholar. Each point is a dated snapshot.
citations73,774As of Nov 6, '26
References
- Stealing Machine Learning Models via Prediction APIsarxiv.org
Coauthorship and copying model functionality through public prediction interfaces.
- ETH Zürich — Florian Tramèr receives USENIX Security Test of Time Awardethz.ch
Foundational model-stealing research, award, current security and privacy research on language models and agents.
Based on public sources. If accuracy is important, verify details using the links or references.
For corrections, updates, or requests to remove information, contact us.
