Research on Method for Fusion and Mapping of Cyberspace Assets Based on Knowledge Graph

The fusion and mapping of cyberspace assets represent an effective means of organizing cyber assets and converging asset defense profiles. However, asset fusion and mapping in the context of Internet exposure encounters numerous challenges, including semantic coreference conflicts in heterogeneous discrete asset attributes, entity wildcard resolution, and false positives in mapping results. Therefore, this study proposes a method for fusion and mapping of cyberspace assets based on knowledge graph. Firstly, a coreference resolution mechanism for asset attributes that leverages the quality of asset intelligence is designed. This mechanism defines core asset accuracy and asset attribute completeness indicators, and integrates asset type weights to quantitatively evaluate asset intelligence quality. This serves as a benchmark for resolving semantic coreference in asset attributes. Secondly, a cyberspace assets knowledge graph ontology based on six-tuples is constructed. We design a triple structure for cyber asset entity representation and establish cyber asset relationship extraction rules based on protocol analysis. Finally, an entity alignment algorithm for false positive domain name assets based on wildcard resolution feature similarity is proposed, leveraging DNS resolution features and service response features to identify wildcard resolution assets, establishes thresholds to determine the range of false positive domain names, and aligns wildcard resolution assets to primary domain name asset entities. Experimental results in real network environments demonstrate that our method effectively addresses challenges including semantic coreference conflicts in asset attributes, entity wildcard resolution, and false positives in asset mapping. This study enhances the completeness and accuracy of cyberspace assets mapping results.