Publications

The latest research and analysis from the Berkeley Risk and Security Lab

Building an AI Red Teaming Discipline

As commercial artificial intelligence models have become increasingly sophisticated, we need to build a discipline around red teaming tools, protocols, and red teamers themselves.

Leah Walker, Jake Hecla, Cara Marie Wagner, Andrew Reddie

Publication: BRSL Blog (Brisk Assessment)
Published: September 3, 2025

Managing Commercial Spyware Through Export Controls

Examination of how multilateral export controls can be used to constrain commercial spyware and address human rights, national security and nonproliferation concerns stemming from the misuse of spyware technologies.

Publication: CLTC White Paper (External Report)
Published: March 1, 2025