These derived models can then be used to generate more data. Experimentally, we demonstrate the efficacy more » of generative sequence analysis techniques on learning the structure of attack graphs, based on a realistic example. Automatically generating such data helps derive/evaluate detection models and ensures reproducibility of results. Training and evaluating cyber systems and machine learning models requires significant, annotated data, which is typically collected and labeled by hand for one-off experiments. In this work, we explore the use of temporal generative models to learn cyber attack graph representations and automatically generate data for experimentation and evaluation. Algorithms that do not require annotated data to derive models are similarly at a disadvantage, because labeled data is still necessary when evaluating performance. However, to generate these models, most algorithms require large amounts of labeled data (i.e., examples of attacks). Additionally, machine learning has shown promise in deriving models that automatically learn indicators of compromise that are more robust than analyst-derived detectors. Currently, performance of cyber defense systems is typically evaluated in a qualitative manner by manually inspecting the results of the system on live data and adjusting as needed. This difficulty largely stems from a lack of labeled attack data that fully explores the potential adversarial space. Rigorous characterization of the performance and generalization ability of cyber defense systems is extremely difficult, making it hard to gauge uncertainty, and thus, confidence.