Skip to content
Longterm Wiki
grant

ETH Zürich — LLM Adversarial Attacks Benchmark

Child of Coefficient Giving

Metadata

Source Tablegrants
Source IDpwgJl8yoai
Descriptionto ETH Zürich, USD 130000, 2024-09
Source URLcoefficientgiving.org/funds/
ParentCoefficient Giving
Children
CreatedMar 12, 2026, 5:54 AM
UpdatedMar 22, 2026, 2:59 AM
SyncedMar 19, 2026, 8:57 PM

Record Data

idpwgJl8yoai
organizationIdCoefficient Giving(organization)
granteeIdETH Zürich
orgEntityIdCoefficient Giving(organization)
orgDisplayName
granteeEntityId
granteeDisplayNameETH Zürich
nameETH Zürich — LLM Adversarial Attacks Benchmark
amount130000
currencyUSD
period
date2024-09
status
sourcecoefficientgiving.org/funds/
notes[Navigating Transformative AI] Open Philanthropy recommended a grant of $130,000 to ETH Zürich to support the development of a benchmark to measure whether LLM agents can design and implement adversarial attacks that overcome defenses described in the academic literature. The project will be led by 
programIdEXpTP-ujq6
dataSourceId

Source Check Verdicts

confirmed95% confidence

Last checked: 4/29/2026

1 → confirmed

Debug info

Thing ID: pwgJl8yoai

Source Table: grants

Source ID: pwgJl8yoai

Parent Thing ID: sid_ULjDXpSLCI