US 12,462,069 B2
Method and a system for checking ownership and integrity of an ai model using distributed ledger technology (DLT)
Manojkumar Somabhai Parmar, Ahmedabad (IN); Shrey Arvind Dabhi, Gujarat (IN); Sunder Naik Anjali, Bangalore (IN); and Mayurbhai Thesia Yash, Gujarat (IN)
Assigned to Robert Bosch GmbH, Stuttgart (DE); and Robert Bosch Engineering and Business Solutions Private Limited, Bangalore (IN)
Appl. No. 18/694,126
Filed by Robert Bosch GmbH, Stuttgart (DE); and Robert Bosch Engineering and Business Solutions Private Limited, Bangalore (IN)
PCT Filed Jul. 15, 2022, PCT No. PCT/EP2022/069875
§ 371(c)(1), (2) Date Mar. 21, 2024,
PCT Pub. No. WO2023/001708, PCT Pub. Date Jan. 26, 2023.
Claims priority of application No. 2021 4103 2309 (IN), filed on Jul. 19, 2021.
Prior Publication US 2024/0403493 A1, Dec. 5, 2024
Int. Cl. G06F 21/64 (2013.01); G06F 21/16 (2013.01); G06N 3/08 (2023.01); G06N 20/10 (2019.01); H04L 9/08 (2006.01); H04L 9/32 (2006.01)
CPC G06F 21/64 (2013.01) [G06F 21/16 (2013.01); G06N 3/08 (2013.01); G06N 20/10 (2019.01); H04L 9/0897 (2013.01); H04L 9/3239 (2013.01); H04L 9/3247 (2013.01)] 10 Claims
OG exemplary drawing
 
1. A method for determining ownership and integrity of an artificial intelligence (AI) model using distributed ledger technology (DLT), wherein processing nodes of a plurality of processing nodes are linked by a distributed ledger (DL) over a network, and the method is performed by any one processing node of the plurality of processing nodes, the method comprising:
embedding a digital watermark in the AI model, during training of the AI model, using first watermark data and a predefined output of the first watermark data;
generating, by using a hashing technique, a full checksum and a selective checksum for the AI model;
registering the AI model on the DL by uploading the full checksum, the selective checksum, the first watermark data, and at least the predefined output of the first watermark data;
receiving, upon the registering of the AI model, a unique model identification (ID) of the AI model;
receiving the AI model, the unique model ID of the AI model, and at least the first watermark data as an input;
checking for registration of the AI model by matching the received unique model ID of the AI model with a stored model ID on the DL;
processing the first watermark data to get a processed output and matching the processed output with the predefined output of the first watermark data;
verifying the full checksum and the selective checksum of the AI model;
calculating an error for the AI model based on the selective checksum verification; and
determining the integrity of the AI model based on the calculated error.