Login| Sign Up| Help| Contact|

Patent Searching and Data


Title:
MODEL OWNERSHIP VERIFICATION METHOD AND APPARATUS, STORAGE MEDIUM AND ELECTRONIC DEVICE
Document Type and Number:
WIPO Patent Application WO/2024/060852
Kind Code:
A1
Abstract:
Disclosed in the present description are a model ownership verification method and apparatus, a storage medium, and an electronic device. The method comprises: adding a specified feature to an original sample, without adjusting the label of the original sample, such that the label of an adjusted sample is the same as that of the original sample corresponding to the adjusted sample; and according to the gradient obtained by inputting the adjusted sample into a model to be verified and the gradient obtained by inputting the adjusted sample into a benign model trained by using the original sample, determining whether a sample for training the model to be verified comes from an edge node. In the method, the label of the adjusted sample is the same as that of the original sample corresponding to the adjusted sample, and therefore, when the ownership of the model to be verified cannot be determined by means of the label, whether the sample for training the model to be verified comes from the edge node is determined by means of different gradient performances of the adjusted sample in the model to be verified and in the benign model, so that the ownership of the model to be verified can be determined more accurately.

Inventors:
LI YIMING (CN)
LIU YAN (CN)
ZHU LINGHUI (CN)
WENG HAIQIN (CN)
JIANG YONG (CN)
XIA SHUTAO (CN)
Application Number:
PCT/CN2023/110871
Publication Date:
March 28, 2024
Filing Date:
August 02, 2023
Export Citation:
Click for automatic bibliography generation   Help
Assignee:
ALIPAY HANGZHOU INF TECH CO LTD (CN)
International Classes:
G06F18/20; G06F18/214; G06F18/22; G06F18/24
Foreign References:
CN115600090A2023-01-13
CN114912513A2022-08-16
CN114120273A2022-03-01
US20210357814A12021-11-18
Attorney, Agent or Firm:
BEIJING BESTIPR INTELLECTUAL PROPERTY LAW CORPORATION (CN)
Download PDF: