most citedBenchmark Early and Red Team Often: A Framework for Assessing and Managing Dual-Use Hazards of AI Foundation Models

3 citations · 4 across the 2 of their papers we have counts for

collaborators
Showing cs.CRShow all

1 paper · 1 filter

cs.CR2024★ 3 cited

Benchmark Early and Red Team Often: A Framework for Assessing and Managing Dual-Use Hazards of AI Foundation Models

Anthony M. Barrett, Krystal Jackson, Evan R. Murphy +2

A concern about cutting-edge or "frontier" AI foundation models is that an adversary may use the models for preparing chemical, biological, radiological, nuclear, (CBRN), cyber, or…