Securing AI Model Weights: Preventing Theft and Misuse of Frontier Models by Sella Nevo, Dan Lahav, Ajay Karpur, Yogev Bar-On, Henry Alexander Bradley, Jeff Alstott ISBN 9781977413376, 1977413374 instant download

Securing AI Model Weights: Preventing Theft and Misuse of Frontier Models by Sella Nevo, Dan Lahav, Ajay Karpur, Yogev Bar-On, Henry Alexander Bradley, Jeff Alstott ISBN 9781977413376, 1977413374 instant download

As frontier artificial intelligence (AI) models — that is, models that match or exceed the capabilities of the most advanced models at the time of their development — become more capable, protecting them from theft and misuse will become more important. The authors of this report explore what it would take to protect model weights — the learnable parameters that encode the core intelligence of an AI — from theft by a variety of potential attackers.
-
Specifically, the authors:
(1) identify 38 meaningfully distinct attack vectors, 
(2) explore a variety of potential attacker operational capacities, from opportunistic (often financially driven) criminals to highly resourced nation-state operations, 
(3) estimate the feasibility of each attack vector being executed by different categories of attackers,
(4) define five security levels and recommend preliminary benchmark security systems that roughly achieve the security levels.