Forecasting Cybersecurity Incidents in Energy Delivery Systems
NOTE: this is no longer an active CREDC research activity.
Entities in various EDS sectors differ significantly in the likelihood that they will be targeted for attack, but we lack good models to identify those most at risk in order to encourage preventive measures. Although machine learning has been used for cyber event detection, coupling machine learning classifiers with externally observable measurements to forecast cyber events in EDS potentially addresses the gap in modeling, and supports Roadmap goals of risk assessment, incident management, and sustainable security. This activity addresses the need for proactive rather than reactive indications of adverse cyber events.
Energy Delivery System (EDS) Gap Analysis
- Forecasting Cybersecurity Incidents in Energy Delivery Systems (2016 Industry Workshop)
Status of Activity
- Activity Leads
- Related Researchers
- Industry Collaborators