CYBER SECURITY

• US 20170109524A1
• Filed: 01/03/2017
• Published: 04/20/2017
• Est. Priority Date: 03/15/2013
• Status: Active Grant

• Current Assignee: KA Holding, LLC (Markel Corporation)
• Original Assignee: Cyberricade, Inc
• Inventors: Kolacinski, Richard M., Angeline, Barry D., Loparo, Kenneth A.
• Granted Patent: US 9,910,980 B2
• Time in Patent Office: Days
• CPC Class Codes: G06F 21/52 during program execution, e.g. stack integrity ; Preventing unwanted data erasure; Buffer overflow
• CPC Class Codes: G06F 21/55 Detecting local intrusion or implementing counter-measures
• CPC Class Codes: G06F 21/552 involving long-term monitoring or reporting
• CPC Class Codes: G06F 21/577 Assessing vulnerabilities and evaluating computer system security
• CPC Class Codes: G06F 2221/034 Test or assess a computer or a system
• CPC Class Codes: G06N 20/00 Machine learning
• CPC Class Codes: G06N 7/01 Probabilistic graphical models, e.g. probabilistic networks
• CPC Class Codes: Y04S 40/20 Information technology specific aspects, e.g. CAD, simulation, modelling, system security

Abstract

Systems and methods that use probabilistic grammatical inference and statistical data analysis techniques to characterize the behavior of systems in terms of a low dimensional set of summary variables and, on the basis of these models, detect anomalous behaviors are disclosed. The disclosed information-theoretic system and method exploit the properties of information to deduce a structure for information flow and management. The properties of information can provide a fundamental basis for the decomposition of systems and hence a structure for the transmission and combination of observations at the desired levels of resolution (e.g., component, subsystem, system).

Claims

1. (canceled)

2. A computer implemented method for detecting cyber physical system behavior, comprising:

utilizing one or more processors and associated memory storing one or more programs for execution by the one or more processors, the one or more programs including instructions for;

receiving data from a sensor associated with the cyber physical system, wherein receiving data includes receiving time series data from the sensor monitoring a cyber-physical system;

constructing a metrization of the data utilizing a data structuring;

determining at least one summary variable from the metrized data, wherein the at least one summary variable is based at least in part upon automata model utilizing a probabilistic grammatical inference;

applying a thermodynamic formalism to the at least one summary variable to classify a plurality of system behaviors;

identifying the system behavior based at least in part on the classified plurality of system behaviors; and

obtaining, by the one or more processors, a baseline of the system behavior associated with the classified plurality of systems behaviors.

3. The method for detecting cyber physical system behavior of claim 2, further comprising detecting an anomalous condition based on a deviation of the system behavior from the baseline.

4. The method for detecting cyber physical system behavior of claim 2, wherein the cyber-physical system is an electrical power grid system.

5. The method for detecting cyber physical system behavior of claim 2, wherein the act of determining at least one summary variable from the metrized data includes an act of discovering common subtrees of a string parse tree via a nonparametric Bayesian clustering method including a Dirichlet Process or a Beta Process or a diffusion map technique.

6. The method for detecting cyber physical system behavior of claim 2, wherein determining at least one summary variable includes a symbolic encoding of the metrized data.

7. The method for detecting cyber physical system behavior of claim 2, wherein the probabilistic grammatical inference comprises an ε

-Machine Reconstruction statistical machine learning technique.

8. The method for detecting cyber physical system behavior of claim 7 wherein the ε

-Machine Reconstruction statistical machine learning technique includes describing a system trajectory as a string of symbols and describing system dynamics in terms of shift dynamics of the associated symbol string

9. The method for detecting cyber physical system behavior of claim 2, including identifying cycles in strings of symbols utilizing pumping lemmas.

10. The method for detecting cyber physical system behavior of claim 3 further comprising:

generating an output indicating the identified system behavior or the anomalous condition.

11. The method for detecting cyber physical system behavior of claim 2, wherein the act of determining includes empirically determining at least one ensemble.

12. The method for detecting cyber physical system behavior of claim 2, wherein applying a thermodynamic formalism includes applying thermodynamic techniques to at least a subset of the sensor data.

13. The method for detecting cyber physical system behavior of claim 2, wherein the data structuring includes a manifold learning technique.

14. The method for detecting cyber physical system behavior of claim 13, wherein the manifold learning technique comprises at least one of a Diffusion Mapping, a bijective mapping or a spectral graph analysis.

15. The method for detecting cyber physical system behavior of claim 2, wherein the at least one summary variable is determined by forming a derivative of a natural variable.

16. The method for detecting cyber physical system behavior of claim 3, wherein detecting an anomalous condition includes at least one of predicting or detecting the presence of an Improvised Explosive Device (IED).

17. A system for detecting cyber physical system behavior, comprising:

a processor and memory coupled to the processor, the processor executes the following executable components;

a data collection component that receives encoded information from the cyber physical system, wherein the encoded information includes time series data representative of the cyber-physical system;

a data assimilation component that decodes the encoded information, via a spectral graph analysis process comprising a diffusion mapping technique, by applying a manifold learning technique to the information to identify system features including at least one summary variable, wherein the data assimilation component applies a thermodynamic formalism to the at least one summary variable to obtain an indication of system behavior; and

an operational component that receives the indication of system behavior and identifies an uncharacteristic system behavior.

18. The system for detecting cyber physical system behavior of claim 17, wherein at least a subset of the encoded information includes at least one of continuous, discrete or transactional cyber physical system dynamics.

19. The system for detecting cyber physical system behavior of claim 17, wherein the operational component provides an output indicating the anomalous system behavior.

20. The system for detecting cyber physical system behavior of claim 17, wherein the data assimilation component utilizes the spectral graph analysis process that includes integrating data across at least one of a continuous physical domain or a discrete physical domains and at least one of a computational cyber domain or a transactional cyber domain.

21. The system for detecting cyber physical system behavior of claim 17, wherein the data assimilation component utilizes a bijective mapping technique.