Cyber Modeling & Simulation

RESEARCH LAB OVERVIEW

Cyber modeling and simulation (M&S) allows the exploration of complex interrelation between humans, software, and hardware systems and how they can lead to vulnerabilities or resilience. The ACI's Cyber Modeling and Simulation Research Lab (CMSRL) enables the exploration of cyber modeling and simulation in decision making and provides context and understanding of cyber risk, allowing for the development of methods and tooling to identify and mitigate vulnerabilities in systems. By creating abstractions of the physical world and using cutting edge tools to support multiple-domain operations, we can examine these interactions and changes in the system overtime and create scalable solutions.

John Pavlik demonstrating the Hololens

Cyber Research, Development, Testing, Evaluation and Assessment
Cyber Training
Cyber Scenario Development and Wargaming
“Digital twin” and “What-if” Evaluations
Cyber Data Generation
AR/VR/MR for Multi-Domain Operations

Tools and Software Include:

PUBLICATIONS

Nack, E. & Bastian, N. (2024). From Simulation to Reality: Navigating Challenges and Opportunities in the Cyber Domain with Sim2Real Techniques. Cyber Security and Information Systems Information Analysis Center (CSIAC) Journal, 8(2): pp. 24-39.

Wong, J., Nack, E., Steelman, Z., Erway, S. & Bastian, N. (2024). A Methodology for Representing and Assessing Artificial Intelligence Decision Aids within Modeling and Simulation. Proceedings of the 2024 SPIE DCS Conference on Artificial Intelligence and Machine Learning for Multi-Domain Operations Applications VI (130510K), pp. 130510K-1 – 130510K-25, SPIE Defense + Commercial Sensing (Volume: 13051).

Schabinger, R., Carlin, C., Mullin, J., Bierbrauer, D., Nack, E., Pavlik, J., Wei, A., Bastian, N. & Ahiskali, M. (2024). Dynamic Reinforcement Learning for Network Defense: Botnet Detection and Eradication. Proceedings of the 2024 SPIE DCS Conference on Artificial Intelligence and Machine Learning for Multi-Domain Operations Applications VI (130511D), pp. 130511D-1 – 130511D-11, SPIE Defense + Commercial Sensing (Volume: 13051).

Nack, E. & Bastian, N. (2023). Synthetic Environments for the Cyber Domain: A Survey on Advances, Gaps and Opportunities. The Cyber Defense Review, 8(2): 91-103.

Mitchell, T., Sheffield, N., Richardson, D., Jensen, B., Nack, E., Cruickshank, I., Thomson, R. & Bastian, N. (2023). An Analytic Framework for Assessing Artificial Intelligence and Assistive Automation Enabled Command and Control Decision Aids for Mission Effectiveness. Proceedings of the 2023 General Donald R. Keith Memorial Capstone Conference, pp. 7-13. SISE.

Bierbrauer, D., Schabinger, R., Carlin, C., Mullin, J., Pavlik, J. & Bastian, N. (2023). Autonomous Cyber Warfare Agents: Dynamic Reinforcement Learning for Defensive Cyber Operations. Proceedings of the 2023 SPIE Conference on Artificial Intelligence and Machine Learning for Multi-Domain Operations Applications V (125380E), pp. 125380E-1 – 125380E-16, SPIE Defense + Commercial Sensing (Volume: 12538).

Hore, S., Shah, A. & Bastian, N. (2023). Deep VULMAN: A Deep Reinforcement Learning-enabled Cyber Vulnerability Management Framework. Expert Systems with Applications, 221(119734): 1-17.

Lin, Z., Pike, T., Bailey, M. & Bastian, N. (2022). A Hypergraph-Based Machine Learning Ensemble Network Intrusion Detection System. arXiv:2211.03933.

Byington, N., Davis, C., Meehan, M., Vincent, C., Woodward, D. & Bastian, N. (2022). Counter-AI Tool System Design for AI System Adversarial Testing and Evaluation. Proceedings of the 2022 General Donald R. Keith Memorial Capstone Conference, pp. 52-57. SISE.

Chalé, M. & Bastian, N. (2022). Generating Realistic Cyber Data for Training and Evaluating Machine Learning Classifiers for Network Intrusion Detection Systems. Expert Systems with Applications, 207(117936): 1-18.

Chandak, Y., Shankar, S., Bastian, N., Castro da Silva, B., Brunskill, E. & Thomas, P. (2022). Off-Policy Evaluation for Action-Dependent Non-Stationary Environments. Proceedings of the 36th Conference on Neural Information Processing Systems, pp. 9217-9232.

Hore, S., Shah, A. & Bastian, N. (2022). An Artificial Intelligence-Enabled Framework for Optimizing the Dynamic Cyber Vulnerability Management Process. Proceedings of the 39th International Conference on Machine Learning, pp. 1-21.

AFFILIATED RESEARCHERS

LTC Nathaniel Bastian, Ph.D.

Division Chief, Data and Decision Sciences | Senior Research Scientist, Army Cyber Institute
MAJ Sean Coffey

Research Scientist, Army Cyber Institute
LTC Matthew Corbett

Senior Research Scientist, Army Cyber Institute
LTC Kyle Luoma

Research Scientist, Army Cyber Institute
Mr. Ryan McNeil

Data Scientist / Engineer, Army Cyber Institute
Mr. Jared Murphy

AI Researcher, Army Cyber Institute
Ms. Emily Nack

Research Lab Manager, Army Cyber Institute
Dr. Aryn Pyke

Senior Research Scientist, Army Cyber Institute
Dr. Robert Thomson

Senior Research Scientist, Army Cyber Institute
MAJ Kenneth Weiss

Research Scientist, Army Cyber Institute

PROJECT SPONSORS