The Los Alamos National Laboratory (LANL)/Missouri University of Science and Technology (S&T) Cyber Security Sciences Institute (CSSI) is a sub-institute of the Information Science and Technology Institute (ISTI) in LANL's National Security Education Center. The primary facility housing CSSI is the export-controlled Natural Computation Laboratory (NC-LAB) facility in the Department of Computer Science at Missouri University of Science and Technology (Missouri S&T), formerly University of Missouri-Rolla (UMR). Since its founding in May 2013, CSSI's research mission has been to create a solid scientific foundation for cyber security research and employ computational intelligence to build robust solutions on that foundation to solve real-world cyber security problems. In particular, CSSI focuses on creating advanced reusable platform technologies which can address emergent problems in the cyber security domain.
CSSI Research Thrusts
Currently CSSI has two research thrusts, namely:
- Network Algorithm Generating Application (NAGA): This thrust focuses on the intersection of evolutionary computation and graph theory for cyber security applications; a proof of concept for operationalizing cyber security R&D from this thrust identified high pay-off access control policy changes on LANL's network by evolving bipartite authentication graph partitions; the end goal of that project is to provide a fully automated tool for optimizing access control policies. Additional applications include evolving network security metrics, custom anomaly detection heuristics, random graph generators, and multi-level graph partitioning algorithms.
- Coevolving Attacker and Defender Strategies for Large Infrastructure Networks (CEADS-LIN): This project focuses on coevolving attacker & defender strategies for enterprise computer networks; a proof of concept for operationalizing cyber security R&D from this thrust demonstrated in simulation that coevolution is capable of implementing a computational game theory solution for adversarial models of network security; currently a high-fidelity emulation framework with intelligent attacker and defender agents is being developed; the end goal is to provide a fully automated solution for identifying high-impact attacks and corresponding defenses.