Knowledge Extraction and Knowledge Graph Construction Based on Campus Security Logss

Campus security log is an important information and data source of protecting campus network security. The analysis and application for campus security log are not inadequate, and security administrator is puzzled by the massive and multi-source security logs. It is difficult to extract implicit knowledge from security logs and to visualize it. How to extract and visualize it has been an urgent problem to be solved in the application of security knowledge engineering. Therefore, a knowledge extraction model based on entity relation triples is proposed in this paper, which deals with structured or semi-structured campus security logs. The knowledge graph of campus security logs is built by the extraction model and visualized in the form of graph. In the experiment, the implicit attack sources, methods and paths of security logs are analyzed and discovered by knowledge graph of campuses security logs. The experimental results demonstrate that the proposed model not only can extract implicit knowledge, but also efficiently visualize knowledge as graph.