US 12,461,509 B2
Systems and methods for artificial intelligence-based security policy development
Timothy C. Mirth, Hudson, OH (US); Taryl J. Jasper, Concord Township, OH (US); Terence S. Tenorio, Solon, OH (US); and Thaddeus A. Palus, Denver, CO (US)
Assigned to Rockwell Automation Technologies, Inc., Mayfield Heights, OH (US)
Filed by Rockwell Automation Technologies, Inc., Mayfield Heights, OH (US)
Filed on Jul. 21, 2022, as Appl. No. 17/870,352.
Prior Publication US 2024/0028009 A1, Jan. 25, 2024
Int. Cl. G05B 19/418 (2006.01)
CPC G05B 19/4185 (2013.01) 20 Claims
OG exemplary drawing
 
1. A non-transitory computer readable medium storing instructions that, when executed by a processor, cause the processor to perform operations comprising:
receiving data from one or more industrial automation systems, wherein the data comprises design artifacts of the one or more industrial automation systems, run time data collected from the one or more industrial automation systems, or both;
inputting the data to a machine learning-based security policy development engine to generate a set of recommended security policies for the one or more industrial automation systems based on the data, wherein the machine learning-based security policy development engine is configured to compare the data to one or more models and generate probabilities of the presence or likelihood of one or more conditions;
receiving the set of recommended security policies for the one or more industrial automation systems output by the security policy development engine;
transmitting the set of recommended security policies to the one or more industrial automation systems for implementation, wherein the one or more industrial automation systems are configured to implement the set of recommended security policies by controlling one or more industrial automation devices to automatically perform one or more remedial actions in response to an event based on the probabilities exceeding one or more threshold values;
anonymizing the data;
transmitting the anonymized data to a service provider;
in response, receiving, from the service provider, training data for the security policy development engine; and
retraining the security policy development engine based on the training data.