We are exploring applying machine learning to the discovery and prediction of network and host properties of systems that monitor, control, and automate industrial processes such as electricity generation, transmission, and distribution. Automated methods for the detailed characterization of such networks and hosts is a necessary first step towards improving the cybersecurity of our nation's critical infrastructure.
Gallagher, B., et al. 2019. "Towards Machine Learning Enabled Mapping Services for Industrial Control Systems." Technical Report. LLNL-TR-795524.
Kelley, B., et al. 2019. "Machine Learning for Mapping Industrial Control System Networks: New Discovery Methods for Infrastructure Cybersecurity." LLNL-POST-771410.
Reed, E., et al. 2019. "Device Identification in Industrial Control Systems." LLNL-POST-785247.
Lawrence Livermore National Laboratory • 7000 East Avenue • Livermore, CA 94550
Operated by Lawrence Livermore National Security, LLC, for the Department of Energy's National Nuclear Security Administration.