Method, systems and apparatus for intelligently emulating factory control systems and simulating response data
A controller emulator, coupled to an interface that exposes the controller emulator to inputs from external sources, provides one or more control signals to a process simulator and a deep learning process. In response, the process simulator simulates response data that is provided to the deep learning processor. The deep learning processor generates expected response data and expected behavioral pattern data for the one or more control signals, as well as actual behavioral pattern data for the simulated response data. A comparison of at least one of the simulated response data to the expected response data and the actual behavioral pattern data to the expected behavioral pattern data is performed to determine whether anomalous activity is detected. As a result of detecting anomalous activity, one or more operations are performed to address the anomalous activity.
1. A computer-implemented method, comprising:
receiving, by a computing system, a training data set comprising one or more control signals, wherein the training data set comprises simulated data for a manufacturing process;
training, by the computing system, a deep learning processor to generate expected response data and expected behavioral pattern data based on the one or more control signals;
analyzing, by the computing system, the training to determine that the deep learning processor has been conditioned;
based on the analyzing, generating, by the computing system, a process simulator configured to simulate response data that reflects target response data during the manufacturing process; and
deploying, by the computing system, the deep learning processor and the process simulator to an intelligent honeypot.
2. The computer-implemented method of claim 1 , wherein the training data set is received from the manufacturing process.
3. The computer-implemented method of claim 1 , wherein receiving, by the computing system, the training data set comprises:
receiving performance metrics for a plurality of stations involved in the manufacturing process.
4. The computer-implemented method of claim 1 , wherein training, by the computing system, the deep learning processor to generate the expected response data and the expected behavioral pattern data based on the one or more control signals comprises:
augmenting the training with additional simulated data from a similar manufacturing process.
5. The computer-implemented method of claim 1 , further comprising:
after deploying the deep learning processor, fine tuning the deep learning processor with additional training data.
6. The computer-implemented method of claim 1 , further comprising:
providing, by the computing system, one or more actual control signals to the process simulator; and
simulating, by the process simulator, the one or more actual control signals to generate actual response data to be provided to the deep learning processor.
7. The computer-implemented method of claim 6 , further comprising:
generating, by the deep learning processor, actual expected response data and actual expected behavioral pattern data based on the one or more actual control signals; and
generating, by the deep learning processor, actual behavioral pattern data based on the actual response data.
8. A system, comprising:
one or more processors; and
a memory having programming instructions stored thereon, which, when executed by the one or more processors, causes a computing system to perform operations, comprising:
receiving a training data set comprising one or more control signals, wherein the training data set comprises simulated data for a manufacturing process;
training a deep learning processor to generate expected response data and expected behavioral pattern data based on the one or more control signals;
analyzing the training to determine that the deep learning processor has been conditioned;
based on the analyzing, generating a process simulator configured to simulate response data that reflects target response data during the manufacturing process; and
deploying the deep learning processor and the process simulator to an intelligent honeypot.
9. The system of claim 8 , wherein the training data set is received from the manufacturing process.
10. The system of claim 8 , wherein receiving the training data set comprises:
receiving performance metrics for a plurality of stations involved in the manufacturing process.
11. The system of claim 8 , wherein training the deep learning processor to generate the expected response data and the expected behavioral pattern data based on the one or more control signals comprises:
augmenting the training with additional simulated data from a similar manufacturing process.
12. The system of claim 8 , wherein the operations further comprise:
after deploying the deep learning processor, fine tuning the deep learning processor with additional training data.
13. The system of claim 8 , wherein the operations further comprise:
providing one or more actual control signals to the process simulator; and
simulating, by the process simulator, the one or more actual control signals to generate actual response data to be provided to the deep learning processor.
14. The system of claim 13 , wherein the operations further comprise:
generating, by the deep learning processor, actual expected response data and actual expected behavioral pattern data based on the one or more actual control signals; and
generating, by the deep learning processor, actual behavioral pattern data based on the actual response data.
15. A non-transitory computer readable medium comprising one or more sequences of instructions, which, when executed by one or more processors, causes a computing system to perform operations comprising:
receiving, by the computing system, a training data set comprising one or more control signals, wherein the training data set comprises simulated data for a manufacturing process;
training, by the computing system, a deep learning processor to generate expected response data and expected behavioral pattern data based on the one or more control signals;
analyzing, by the computing system, the training to determine that the deep learning processor has been conditioned;
based on the analyzing, generating, by the computing system, a process simulator configured to simulate response data that reflects target response data during the manufacturing process; and
deploying, by the computing system, the deep learning processor and the process simulator to an intelligent honeypot.
16. The non-transitory computer readable medium of claim 15 , wherein the training data set is received from the manufacturing process.
17. The non-transitory computer readable medium of claim 15 , wherein receiving, by the computing system, the training data set comprises:
receiving performance metrics for a plurality of stations involved in the manufacturing process.
18. The non-transitory computer readable medium of claim 15 , wherein training, by the computing system, the deep learning processor to generate the expected response data and the expected behavioral pattern data based on the one or more control signals comprises:
augmenting the training with additional simulated data from a similar manufacturing process.
19. The non-transitory computer readable medium of claim 15 , further comprising:
after deploying the deep learning processor, fine tuning the deep learning processor with additional training data.
20. The non-transitory computer readable medium of claim 15 , further comprising:
providing, by the computing system, one or more actual control signals to the process simulator; simulating, by the process simulator, the one or more actual control signals to generate actual response data to be provided to the deep learning processor;
generating, by the deep learning processor, actual expected response data and actual expected behavioral pattern data based on the one or more actual control signals; and
generating, by the deep learning processor, actual behavioral pattern data based on the actual response data.