# US 2021/0084056 A1 · Replacing virtual sensors with physical data after cyber-attack neutralization

> Agents: this data is available as JSON from the patentgrep API and MCP server — see https://patentgrep.com/llms.txt

- Number: US 2021/0084056 A1
- Document ID: US20210084056A1
- Status: Published application
- Kind: A1
- Application number: 16/574,558
- Filed: 2019-09-18
- Published: 2021-03-18
- Earliest claimed: 2019-09-18
- Assignees: General Electric Company
- Applicants: General Electric Company
- Inventors: Masoud ABBASZADEH; Mustafa Tekin DOKUCU; Justin Varkey JOHN
- Web page: https://patentgrep.com/patent/US20210084056A1

## CPC

- H04L 63/1416: {Event detection, e.g. attack signature detection}
- G06N 20/00: Machine learning
- H04L 9/0858: {Details about key distillation or coding, e.g. reconciliation, error correction, privacy amplification, polarisation coding or phase coding}
- H04L 63/1466: {Active attacks involving interception, injection, modification, spoofing of data unit addresses, e.g. hijacking, packet injection or TCP sequence number attacks}
- G06N 7/01: Probabilistic graphical models, e.g. probabilistic networks
- G06N 20/10: using kernel methods, e.g. support vector machines [SVM]
- H04L: TRANSMISSION OF DIGITAL INFORMATION, e.g. TELEGRAPHIC COMMUNICATION (arrangements common to telegraphic and telephonic communication H04M)
- G06N: COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS

## Abstract

An industrial asset may have a plurality of monitoring nodes, each monitoring node generating a series of monitoring node values over time representing current operation of the industrial asset. An abnormality detection computer may determine that an abnormal monitoring node is currently being attacked or experiencing a fault. Responsive to an indication that a monitoring node is currently being attacked or experiencing a fault, the system may automatically replace monitoring node values from the at least one abnormal monitoring node currently being attacked or experiencing a fault with virtual node values. The system may also determine when the abnormal monitoring node or nodes will switch from the virtual node values back to monitoring node values.

## Claims

### Claim 1

A system to protect an industrial asset, comprising:
a plurality of monitoring nodes, each monitoring node generating a series of monitoring node values over time that represent a current operation of the industrial asset;
an abnormality detection computer to determine that at least one abnormal monitoring node is currently being attacked or experiencing a fault; and
a virtual sensor estimator, coupled to the plurality of monitoring nodes and the abnormality detection computer, to:
(i) responsive to an indication that the at least one abnormal monitoring node is currently being attacked or experiencing a fault, automatically replace monitoring node values from the at least one abnormal monitoring node currently being attacked or experiencing a fault with virtual node values, and
(ii) determine when the abnormal monitoring node or nodes will switch from the virtual node values back to monitoring node values.

### Claim 2 (depends on 1)

The system of claim 1, wherein the determination of when the abnormal monitoring node or nodes will switch from the virtual node values back to the monitoring node values is based at least in part on an attestation from a human operator.

### Claim 3 (depends on 1)

The system of claim 1, wherein the determination of when the abnormal monitoring node or nodes will switch from the virtual node values back to the monitoring node values is performed automatically.

### Claim 4 (depends on 1)

The system of claim 1, wherein the virtual sensor estimator is further to:
(iii) responsive to said determination, switch the abnormal node or nodes from the virtual node values back to monitoring node values.

### Claim 5 (depends on 1)

The system of claim 1, wherein the determination of when the abnormal monitoring node or nodes will switch from the virtual node values back to the monitoring node values is based at least in part on a size of a virtual sensing residual.

### Claim 6 (depends on 1)

The system of claim 1, wherein the determination of when the abnormal monitoring node or nodes will switch from the virtual node values back to the monitoring node values is based at least in part on a global status remaining normal.

### Claim 7 (depends on 1)

The system of claim 1, wherein the determination of when the abnormal monitoring node or nodes will switch from the virtual node values back to the monitoring node values is based at least in part on a sensor ranking list.

### Claim 8 (depends on 1)

The system of claim 1, wherein the determination of when the abnormal monitoring node or nodes will switch from the virtual node values back to the monitoring node values is based at least in part on an external input indicating that no network intrusion is currently active.

### Claim 9 (depends on 8)

The system of claim 8, wherein the external input indication that no network intrusion is currently active is based on network monitoring using supervised or unsupervised anomaly detection methods.

### Claim 10 (depends on 8)

The system of claim 8, wherein the external input indication that no network intrusion is currently active is based on network intrusion detection.

### Claim 11 (depends on 10)

The system of claim 10, wherein the network intrusion detection is based on quantum key distribution.

### Claim 12

A computerized method to protect an industrial asset associated with a plurality of monitoring nodes, each monitoring node generating a series of monitoring node values over time that represent current operation of the industrial asset, comprising:
determining, by an abnormality detection computer, that at least one abnormal monitoring node is currently being attacked or experiencing a fault;
responsive to an indication that the at least one abnormal monitoring node is currently being attacked or experiencing a fault, automatically replacing monitoring node values from the at least one abnormal monitoring node currently being attacked or experiencing a fault with virtual node values; and
determining when the abnormal monitoring node or nodes will switch from the virtual node values back to monitoring node values.

### Claim 13 (depends on 12)

The system of claim 12, wherein the determination of when the abnormal monitoring node or nodes will switch from the virtual node values back to the monitoring node values is based at least in part on an attestation from a human operator.

### Claim 14 (depends on 12)

The method of claim 12, wherein the determination of when the abnormal monitoring node or nodes will switch from the virtual node values back to the monitoring node values is performed automatically.

### Claim 15 (depends on 12)

The method of claim 12, further comprising:
responsive to said determination, switching the abnormal node or nodes from the virtual node values back to monitoring node values.

### Claim 16

A non-transitory, computer-readable medium storing instructions that, when executed by a computer processor, cause the computer processor to perform a method to protect an industrial asset associated with a plurality of monitoring nodes, each monitoring node generating a series of monitoring node values over time that represent current operation of the industrial asset, the method comprising:
determining, by an abnormality detection computer, that at least one abnormal monitoring node is currently being attacked or experiencing a fault;
responsive to an indication that the at least one abnormal monitoring node is currently being attacked or experiencing a fault, automatically replacing monitoring node values from the at least one abnormal monitoring node currently being attacked or experiencing a fault with virtual node values; and
determining when the abnormal monitoring node or nodes will switch from the virtual node values back to monitoring node values.

### Claim 17 (depends on 16)

The medium of claim 16, wherein the determination of when the abnormal monitoring node or nodes will switch from the virtual node values back to the monitoring node values is based at least in part on a size of a virtual sensing residual.

### Claim 18 (depends on 16)

The medium of claim 16, wherein the determination of when the abnormal monitoring node or nodes will switch from the virtual node values back to the monitoring node values is based at least in part on a global status remaining normal.

### Claim 19 (depends on 16)

The medium of claim 16, wherein the determination of when the abnormal monitoring node or nodes will switch from the virtual node values back to the monitoring node values is based at least in part on a sensor ranking list.

### Claim 20 (depends on 16)

The medium of claim 16, wherein the determination of when the abnormal monitoring node or nodes will switch from the virtual node values back to the monitoring node values is based at least in part on an external input indicating that no network intrusion is currently active.

### Claim 21 (depends on 20)

The medium of claim 20, wherein the external input indication that no network intrusion is currently active is based on at least one of: (i) network monitoring using supervised or unsupervised anomaly detection methods, (ii) network intrusion detection, and (iii) quantum key distribution.
