“In my current work, I study the worst-case behavior of Large Language Models from an adversarial perspective, to understand and mitigate long-term threats to the safety and privacy of users.”In their own words: floriantramer.com
Assistant professor of computer science at ETH Zurich leading the SPY Lab; works on computer security, machine learning and cryptography, including the worst-case adversarial behaviour of large language models.
Show detailsHide details
Received $945k from 4 funders
’24
’25
’26
Checked 25 Oct 2026
Money flows
Where their money came from and where it went. Pick years and what to show; hover a box or ribbon for details, click one to focus it, click the background to see everything.
Funded by
All grants
4 grants totalling $945k, newest first.
2026 1 grant · $370k
2025 1 grant · $370k
| Date | Funder | Amount | Purpose |
|---|---|---|---|
| 11 Feb 2025 | Science of Trustworthy AI | ~$370k | Science of Trustworthy AI — AI Safety Science (Feb 2025 cohort): ETH Zurich. Project: Formalizing Prompt Injection Defenses. One of 27 AI Safety Science awards; per-project amount undisclosed. — Science of Trustworthy AI — AI Safety Science (Feb 2025 cohort) source |
2024 2 grants · $205k
| Date | Funder | Amount | Purpose |
|---|---|---|---|
| Sep 2024 | Coefficient Giving | $130k | LLM Adversarial Attacks Benchmark (Florian Tramér) source |
| May 2024 | Foresight Institute: Funding | ~$75k | AI Safety Research — formalizing threat models for using cryptography to secure AI applications. Focus area: Security/Cryptography. First listed on foresight.org/ai-safety by May 2024. — AI Safety Grants (Underexplored A source |