Center for Statistics and Machine Learning
Faculty Lunchtime Seminars
Featuring CSML Affiliated Faculty Members
Speaker: Peter Henderson, Princeton University
Title:      AI Safety, Governance, and Evaluation When Models Can be Customized
Day:       September 24, 2024
Place     CSML, Bendheim House, 26 Prospect Ave, Room 103
Time:     12:30-1:30 PM  Lunch available from12:15 with RSVP to csml@princeton.edu     
Host:     Peter Ramadge, CSML Director, Gordon Y.S. Wu Professor of Engineering
Event info: https://csml.princeton.edu/events/ai-safety-governance-and-evaluation-when-models-can-be-customized

Abstract: New regulatory requirements would have AI model developers assure that models cannot induce harms even when downstream users can modify the model in different ways. This talk will examine these regulatory regimes, the challenges of such pre-deployment evaluation requirements, and potential paths forward for addressing safety concerns.