Depth model privacy protection method and device oriented to member reasoning attack and based on parameter sharing
A deep model and privacy protection technology, applied in the field of deep model privacy protection based on parameter sharing, can solve the problems of reducing the prediction ability of the target model, high time complexity, and difficulty in convergence of the target model.
- Summary
- Abstract
- Description
- Claims
- Application Information
AI Technical Summary
Problems solved by technology
Method used
Image
Examples
Embodiment Construction
[0025] In order to make the object, technical solution and advantages of the present invention clearer, the present invention will be further described in detail below in conjunction with the accompanying drawings and embodiments. It should be understood that the specific embodiments described here are only used to explain the present invention, and do not limit the protection scope of the present invention.
[0026] The technical idea of the present invention is: model overfitting is considered to be the main reason for member reasoning attacks, each training sample can have an impact on the prediction of the model, and this impact is reflected in the parameters of the model, which record the training The relevant information of the sample, and the prediction result is calculated from the model parameters. The present invention reduces the influence of training set samples on model parameters through the method of sharing parameters, can effectively alleviate the degree of ...
PUM
Abstract
Description
Claims
Application Information
- R&D Engineer
- R&D Manager
- IP Professional
- Industry Leading Data Capabilities
- Powerful AI technology
- Patent DNA Extraction
Browse by: Latest US Patents, China's latest patents, Technical Efficacy Thesaurus, Application Domain, Technology Topic, Popular Technical Reports.
© 2024 PatSnap. All rights reserved.Legal|Privacy policy|Modern Slavery Act Transparency Statement|Sitemap|About US| Contact US: help@patsnap.com