High-Fidelity Model-Driven Deception Platform for Cyber-Physical Systems
AssigneeBattelle Memorial Institute
InventorsThomas W. Edgar, Draguna L. Vrabie, William J. Hofer, Kathleen E. Nowak
Life of this patent
Estimating the term…
Loading patent…
AssigneeBattelle Memorial Institute
InventorsThomas W. Edgar, Draguna L. Vrabie, William J. Hofer, Kathleen E. Nowak
Estimating the term…
Methods are described for protecting a cyber-physical system against a potential attacker of the system. The methods include a method of generating a plurality of examples for a training data set and training a system model using the training data set to generate a decoy configured to generate a synthetic output that mimics historical outputs generated by the system for a given historical system context. Also described is a method including receiving a system context of a cyber-physical system; receiving an inquiry into the system by a potential attacker; applying a system model to the system context and the inquiry; obtaining from the system model a synthetic output that mimics how a component of the system would respond to the inquiry given the system context; and providing the synthetic output to the potential attacker.
A method comprising:
The method of claim I, wherein receiving example historical information about the cyber-physical system comprises:
A method comprising:
Dependencies are inferred from the claim text.