Securing AI Model Weights: Preventing Theft and Misuse of Frontier Models

Description

The authors describe how to secure the weights of frontier artificial intelligence and machine learning models (that is, models that match or exceed the capabilities of the most advanced models at the time of their development).

• Author: Sella Nevo, Dan Lahav, Ajay Karpur, Yogev Bar-On, Henry Alexander Bradley
• Publisher: Rand Corporation
• Published: 2024-05-30
• Pages: 130
• ISBN-13: 9781977413376