“the first comprehensive benchmark for systematically evaluating backdoor threats in text-generation LLMs”In its own words: arxiv.org
Open benchmark for evaluating backdoor attacks on, and defences for, text-generating large language models.
Show detailsHide details
Received $50k from 1 funder
Checked 7 Nov 2026
Money flows
Where its 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
1 grant totalling $50k, newest first.
2025 1 grant · $50k
| Date | Funder | Amount | Purpose |
|---|---|---|---|
| Apr 2025 | Science of Trustworthy AI | $50k | SafeBench competition first prize ($50,000): backdoor attacks on LLMs. Prize pool $250,000 sponsored by Schmidt Sciences, run by the Center for AI Safety; winners page undated, AgentDojo announced its win on 29 Apr 2025. source |