A Playbook for Securing AI Model Weights
Nevo, Sella, Lahav, Dan, Karpur, Ajay, Bar-On, Yogev, Bradley, Henry Alexander, Alstott, Jeff · RAND Corporation eBooks · 2024
Researchers developed recommendations for securing the weights of artificial intelligence models that match or exceed the frontier capabilities. These recommendations can be used by developers and policymakers to ensure the security of AI systems.