Graph Matching Intrusion Detection for the Insider Threat
Small Business Information
11675 Jollyville Road, Suite 300, Austin, TX, 78759
AbstractWe propose the Graph Matching Intrusion Detection (GMID) system, a novel approach to detecting insider and coordinated insider-outsider threats based on our algorithms for solving the subgraph isomorphism (graph matching) problem. GMID performs datafusion on information from dense sensor networks inside and outside the secured system to build a graph representation of network topology, user activity, and network state. Threat patterns are represented as graphs, and our graph matching algorithmsquickly identify suspicious activity within the sensed network state. The GMID approach provides new capabilities for
* information listed above is at the time of submission.