US 11,775,347 B2
Method for implanting a watermark in a trained artificial intelligence model for a data processing accelerator
Yueqiang Cheng, Sunnyvale, CA (US); and Yong Liu, Sunnyvale, CA (US)
Assigned to BAIDU USA LLC, Sunnyvale, CA (US); and KUNLUNXIN TECHNOLOGY (BEIJING) COMPANY LIMITED, Beijing (CN)
Filed by Baidu USA LLC, Sunnyvale, CA (US); and KUNLUNXIN TECHNOLOGY (BEIJING) COMPANY LIMITED, Beijing (CN)
Filed on Oct. 10, 2019, as Appl. No. 16/598,129.
Prior Publication US 2021/0109790 A1, Apr. 15, 2021
This patent is subject to a terminal disclaimer.
Int. Cl. G06F 9/50 (2006.01); G06N 5/04 (2023.01); G06N 20/10 (2019.01); G06F 21/16 (2013.01)
CPC G06F 9/5027 (2013.01) [G06F 21/16 (2013.01); G06N 5/04 (2013.01); G06N 20/10 (2019.01)] 20 Claims
OG exemplary drawing
 
1. A computer-implemented method performed by a data processing (DP) accelerator, the method comprising:
receiving, at the DP accelerator, first data representing an artificial intelligence (AI) model that has been previously trained from a host processor;
receiving, at the DP accelerator, a request to implant a watermark in the AI model from the host processor, the request including a watermark algorithm identifier (ID) selected by the host processor;
generating the watermark using a watermark algorithm identified by the watermark algorithm ID;
implanting, by the DP accelerator, the generated watermark within the AI model; and
transmitting second data representing the AI model having the watermark implanted therein to the host processor.