Stanford University — LLM Cybersecurity Benchmark

Organization:
Stanford University
Award Date:
07/2024
Amount:
$2,937,000
Purpose:
To support research to develop a benchmark for the cyberoffense capabilities of LLM agents.

Open Philanthropy recommended a grant of $2,937,000 to Stanford University to support research to develop a benchmark for the cybersecurity capabilities of large language model (LLM) agents, led by Dr. Percy Liang.

This grant was funded via a request for proposals for projects benchmarking LLM agents on consequential real-world tasks and falls within Open Philanthropy’s focus area of potential risks from advanced artificial intelligence.

Read more: