cover image: Exploring red teaming to identify new and emerging risks from AI foundation models

20.500.12592/9s3gnd

Exploring red teaming to identify new and emerging risks from AI foundation models

31 Oct 2023

RAND Europe and the Centre for Long-Term Resilience organised a virtual workshop to inform UK government thinking on policy levers to identify risks from artificial intelligence foundation models in the lead up to the AI Safety Summit in November 2023. The workshop focused on the use of red teaming for risk identification and brought together a range of participants. The ideas discussed at the workshop have been summarised in this report.
artificial intelligence emerging technologies science and technology legislation science, technology, and innovation policy

Authors

Ang, Cecilia, Politi, Chryssa, Gunashekar, Salil, Wade, Imogen, Guest, Ella, Whittlestone, Jess, Zakaria, Sana, Hicks, Marie-Laure, Ohrvik-Stott, Jacob

Division
RAND Europe
Pages
29
Published in
United States
RAND Identifier
CF-A3031-1
RAND Type
report
Rights
RAND Corporation
Series
Conference Proceedings
Source
https://www.rand.org/pubs/conf_proceedings/CFA3031-1.html

Tables

Related Topics

All