Fiscal Year	2013
Division	Graduate School of Engineering & Applied Science
Department	Electrical & Computer Engineering
Investigator(s)	Pace, Phillip E.
Sponsor	Office of Naval Research (Navy)
Summary	The research will answer the following question: Given various cyber wargaming datasets from NPS’ (and other organizations’) simulations/experiments, can algorithms be developed to learn the initial conditions of nonlinear stochastic Detect-Identify-Predict-React (DIPR) intelligence automation systems so that cyber behaviors can be automatically detected? To carry out this, this research will perform the following steps: (1) Research and propose the initial foundations (building blocks) for intelligence automation learning theory. (2) Research and select available datasets for cyber wargaming scenarios. (3) Manually define initial conditions of the DIPR intelligence automation systems for cyber behaviors within cyber wargaming (that will be improved upon using learners). (4) Develop and validate new learners (learning algorithms) using selected cyber datasets. (5) Perform parameter analysis on each algorithm for empirically determining stability, repeatability, accuracy for each method. (6) Begin steps toward defining and proving optimality of selected learning algorithm with theoretical analysis
Keywords
Publications	Publications, theses (not shown) and data repositories will be added to the portal record when information is available in FAIRS and brought back to the portal
Data	Publications, theses (not shown) and data repositories will be added to the portal record when information is available in FAIRS and brought back to the portal