Cyber Reactive Adversary Framework for Training (CRAFT)

Networks have become a critical battleground for military operations as adversaries become increasingly prolific and proficient at cyber warfare. Despite this, cyber training has remained focused on large-scale exercises that are expensive and time-consuming, and ultimately too infrequent. The DoD is addressing this gap with the Persistent Cyber Training Environment (PCTE) to rapidly configure controlled virtual environments for training anytime, anywhere. However, PCTE currently requires human experts to control adversary cyber operations forces (OPFOR). Providing PCTE with automated adversaries will reduce the cost and increase the frequency of training opportunities. To address these needs, and based on our Phase I success, we will develop and thoroughly evaluate the Cyber Reactive Adversary Framework for Training (CRAFT), a reactive agent framework and execution engine that inserts dynamic adversary behaviors into PCTE and provides assessment and authoring tools for instructors to understand and customize the training experience. Based on our Phase I success, we will develop three key components of CRAFT: (1) an Adaptive Adversary Framework that uses reactive behavior modeling to provide realistic, dynamic, and customized adversary behavior for meeting training objectives; (2) a Cyber Execution Engine (CEE) that integrates adversary agents with tools in the virtual network environment; and (3) an Instruction Support Suite that provides tools for configuring, tracking, adjusting, and revising adversary behaviors to provide effective training. Combining these components, CRAFT provides a revolutionary capability to insert reactive, adaptive adversary agents in the virtual networks of PCTE, understand and adjust agent outcomes to meet training objectives, and revise behaviors to produce new threats as adversaries evolve.