Machine Unlearning Doesn't Do What You Think: Lessons for Generative AI Policy, Research, and Practice
We articulate fundamental mismatches between technical methods for machine unlearning
in Generative AI, and documented aspirations for broader impact that these methods could …
in Generative AI, and documented aspirations for broader impact that these methods could …
AI Red Teaming through the Lens of Measurement Theory
A Chouldechova, AF Cooper, A Palia, D Vann… - Neurips Safe Generative … - openreview.net
AI Red teaming--ie, simulating attacks on computer systems to identify vulnerabilities and
improve defenses--can yield both qualitative and quantitative information about generative …
improve defenses--can yield both qualitative and quantitative information about generative …