登入選單
返回Google圖書搜尋
其他書名
Preventing Theft and Misuse of Frontier Models
出版Rand Corporation, 2024-05-30
主題Computers / Artificial Intelligence / GeneralComputers / Data Science / GeneralTechnology & Engineering / GeneralTECHNOLOGY & ENGINEERING / General
ISBN19774133749781977413376
URLhttp://books.google.com.hk/books?id=oHUbEQAAQBAJ&hl=&source=gbs_api
EBookSAMPLE
註釋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.