公开(公告)号：US20240211609A1

公开(公告)日：2024-06-27

申请号：US17915705

申请日：2022-03-22

Applicant: BEIJING BAIDU NETCOM SCIENCE TECHNOLOGY CO., LTD.

Inventor： Shuangyan YUE ,  Zhongkai FAN

IPC: G06F21/60 ,  G06F21/64

CPC classification number: G06F21/602 ,  G06F21/64

Abstract: A method of protecting a model, which relates to a field of computer, a field of artificial intelligence, and may be applied to an AI model protection scenarios. The method includes: generating a WASM file for providing a runtime environment for a target model, the WASM file containing a corresponding model inference algorithm and security verification algorithm, wherein the security verification algorithm is configured to perform at least one security verification operation to protect the target model, the at least one security verification operation is selected from: a verification of a host environment; a verification of an integrity of the WASM file; a verification of an integrity of the model file generated corresponding to an original model file of the target model; a timeout verification of a specified inference process during a model inference process; or a timeout verification of an entire inference process during the model inference process.