Member reasoning attack-oriented deep model privacy protection method based on abnormal point detection
A deep model, privacy protection technology, applied in digital data protection, biological neural network model, electrical digital data processing, etc.
- Summary
- Abstract
- Description
- Claims
- Application Information
AI Technical Summary
Problems solved by technology
Method used
Image
Examples
Embodiment Construction
[0050] The present invention will be further described in detail below with reference to the accompanying drawings and embodiments. It should be noted that the following embodiments are intended to facilitate the understanding of the present invention, but do not limit it in any way.
[0051] The technical idea of the present invention is: model overfitting is the main reason for member reasoning attacks, through the regularization method, the degree of overfitting of the target model is alleviated, and the performance of member reasoning attacks is reduced, but at this time there are still a small number of samples that are vulnerable to Membership inference attack. In order to further improve the defense performance, the present invention detects abnormal samples, finds out samples that are vulnerable to member reasoning attacks, deletes these abnormal samples from the training set of the model, and retrains the target model, which can effectively defend against member reas...
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