Skip to content
Longterm Wiki

ETH Zurich — Research on Prompt Injection Attacks

$20K
Funder
Recipient
ETH ZüRich
Program
Date
Jun 2025
Data source
Source
Notes

[Navigating Transformative AI] Open Philanthropy recommended a grant of $20,000 to ETH Zurich to support a project to develop reinforcement learning techniques for generating prompt injection attacks against LLM agents, led by Xin Chen and Professor Florian Tramer. This falls within our focus area of potential risks from advanced artificial intelligence.

Other Grants by Coefficient Giving

2625
Showing 10 of 2625 grants
ETH Zurich — Research on Prompt Injection Attacks | Coefficient Giving | Grants | Longterm Wiki