Weighted heterogeneous graph-oriented malicious behavior identification method and system and storage medium
An identification method and heterogeneous technology, applied in the field of network security, can solve the problems of poor generalization ability, reduce the accuracy of malicious behavior identification tasks, and not make full use of relational attributes, and achieve the effect of improving accuracy.
- Summary
- Abstract
- Description
- Claims
- Application Information
AI Technical Summary
Problems solved by technology
Method used
Image
Examples
Embodiment
[0057]Such asfigure 1 ,figure 2 As shown, the present invention, a method for identifying malicious behaviors for weighted heterogeneous graphs, includes the following steps:
[0058]S1. Construct an inductive graph neural network model, specifically:
[0059]In this embodiment, the inductive graph neural network model includes a subgraph extraction module, a plurality of feature vector generation and fusion modules, and a classification learning module; the feature vector generation and fusion module includes a MalSage layer and a subgraph feature fusion layer; The MalSage layer includes M MalConv layers, which act on M subgraphs respectively, seeimage 3 ; The classification learning module includes a fully connected layer and a Softmax layer.
[0060]In this embodiment, the input of the inductive graph neural network model is a weighted heterogeneous graph constructed based on the malicious behavior data set, the original feature vector of the node, and multiple meta-paths defined on the h...
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