US 11,740,940 B2
Method and system for making an artifical intelligence inference using a watermark-inherited kernel 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. 16/598,318.
Prior Publication US 2021/0109793 A1, Apr. 15, 2021
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 from a host processor, an artificial intelligence (AI) model that has been previously trained and a set of input data;
receiving, at the DP accelerator from the host processor, a watermark kernel that is capable of inheriting a watermark;
executing the watermark kernel within the DP accelerator on the AI model and the set of input data, wherein the watermark kernel, when executed, is configured to:
generate a new watermark by inheriting an existing watermark from a data object of the set of input data or the AI model, wherein the watermark kernel is configured to:
extract the existing watermark from the data object of the set of input data or the AI model to obtain an inherited watermark, the existing watermark embedded in the received AI model or the set of input data; and
generate the new watermark using the inherited watermark,
perform an AI inference using the AI model based on the input data to generate output data, and
implant the new watermark within the output data; and
transmitting output data having the new watermark implanted therein to the host processor.