Knowledge Graph for Cyber Threat Inference
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
The increasing amount of information in cyberspace, including deep web and dark web data, poses challenges in identifying and analyzing relationships relevant to crimes and threats due to the lack of standardized data formats, making it difficult to infer circumstances related to crimes.
Innovation Solution
A knowledge-based graph is created using a taxonomy graph for classification and an entity graph for relationships, which updates and infers relevance by processing data from various sources, including normal and special web browsers, to analyze and identify connections between information objects.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Loss of information
If data from deep web and dark web are collected and analyzed, then the completeness of crime-related information is improved, but the complexity of data processing and analysis increases
Solution Approach 1:
The patent segments the complex data processing task into multiple components: data collection from various sources (normal web, deep web, dark web), data storage in standardized format, graph construction from stored data, and graph analysis for crime inference. This segmentation allows each component to be handled independently, reducing overall processing complexity while maintaining information completeness.
Solution Approach 2:
The patent introduces an intermediary standardized data format as a mediator between raw collected data and the graph analysis system. Collected data from diverse sources is first converted to a standardized format before being used to construct the graph, which simplifies subsequent analysis operations and reduces processing complexity.
2Measurement precision
If a knowledge-based graph is constructed to analyze relationships, then the accuracy of crime circumstance inference is improved, but the time required for data processing increases
Solution Approach 1:
The patent performs preliminary actions by pre-construction a knowledge-based graph from collected data and storing it in a standardized format. This pre-processed graph structure is then reused for multiple analysis queries, avoiding repeated full-data processing and reducing the time required for subsequent crime circumstance inference while maintaining accuracy.
3Ease of operation
If standardized data format is implemented for all web data, then the ease of data integration is improved, but the complexity of data standardization process increases
Solution Approach 1:
The patent implements a universal standardized data format that can accommodate data from multiple sources (normal web, deep web, dark web) with different structures and formats. This single standardized format serves multiple functions: storing diverse data types, enabling graph construction, and supporting analysis operations, thereby simplifying data integration despite the complexity of the standardization process.
Data Source
AI summary
The present invention relates to a method for processing a knowledge graph in a data processing apparatus, comprising the steps of: (a) creating a knowledge graph including a taxonomy graph for a classification system of information objects and an entity graph for a relationship between specific information object instances; (b) updating the knowledge graph by reflecting the information objects extracted from a database in the knowledge graph; and (c) inferring the relevance of a random information object by using the updated knowledge graph.