GHOSTS in the Machine: A Framework for Cyber-Warfare Exercise NPC Simulation
December 2018 • Technical Report
Dustin D. Updyke, Geoffrey B. Dobson, Thomas G. Podnar, Luke J. Osterritter, Benjamin L. Earl, Adam D. Cerini
This report outlines how the GHOSTS ((G)eneral HOSTS) framework helps create realism in cyber-warfare simulations and discusses how it was used in a case study.
Software Engineering Institute
CMU/SEI Report Number
DOI (Digital Object Identifier):10.1184/R1/12363029.v1
This report introduces the GHOSTS ((G)eneral HOSTS) framework, the purpose of which is to create a high level of realism in cyber-warfare exercises by establishing and building behaviorally accurate, autonomous non-player characters (NPCs). The report outlines how the GHOSTS framework accomplishes the creation of simulations in which NPCs realistically represent a vast array of possible encounters and outcomes. The report concludes with a discussion of a case study in which the GHOSTS framework was used. Participants in the exercise reported high levels of realism, which in turn correlated with higher ratings for training value. These results indicate that the GHOSTS framework can be used to create training of the highest quality, effectively preparing cyber-warfare teams for success in real-world situations.