UC Berkeley — Adversarial Robustness Research (Aditi Raghunathan)

Organization:
UC Berkeley
Award Date:
08/2021
Amount:
$101,064
Purpose:
To support postdoctoral research by Aditi Raghunathan on adversarial robustness as a means to improve AI safety.

Open Philanthropy recommended a grant of $101,064 to UC Berkeley to support postdoctoral research by Aditi Raghunathan on adversarial robustness as a means to improve AI safety.

This falls within Open Philanthropy's focus area of potential risks from advanced artificial intelligence.

Read more: