griDNA is designed to protect distributed critical infrastructure systems such as power grids, pipelines, and transportation networks against disruptions caused by cyber-attacks or system failures. The technology continuously gathers and analyzes system data alerting operators and defenders with early detection of abnormal behavior that signals potential trouble, whether it stems from inadvertent equipment failures or malicious cyber attacks.

The technology provides system operators and defenders with a deeply informative and multi-level cyber-physical situational awareness (CPSA). The collected data represent the infrastructure’s physical (physics-based) processes as well as the cyber network activity supporting the system. Data gathering and analysis is also strategically structured to retrieve information at the “local” level of individual components, the “enclave” level of subsidiary networks, and the “global” level of multiple, interconnected systems. Thus, griDNA is uniquely suitable for monitoring and detection within distributed and interconnected critical infrastructure systems through its flexible granularities.

These data sets are correlated and analyzed using advanced data fusion and artificial intelligence (AI) techniques. The AI analysis, specifically autoencoder neural networks, identifies patterns in the cyber-physical interdependencies and can be used to characterize the expected system behavior.

The technology’s cyber-physical system characterization not only bolsters critical infrastructure cybersecurity and resilience but can also be used to improve planning (e.g., which parts of the system require more redundancy) as well as operation (e.g., certain critical control components are impacted by communication latency delays). While griDNA has been developed with the electric grid application, it can be extended to any critical infrastructure system that relies on physics-based processes and operational networking.