# US 11,443,036 B2 · Facial recognition based security by a management controller

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

- Number: US 11,443,036 B2
- Document ID: US11443036B2
- Status: Granted
- Kind: B2
- Application number: 16/526,388
- Filed: 2019-07-30
- Published: 2021-02-04
- Granted: 2022-09-13
- Earliest claimed: 2019-07-30
- Assignees: Hewlett Packard Enterprise Development LP
- Applicants: Hewlett Packard Enterprise Development LP
- Inventors: Naysen Robertson; Sai Rahul Chalamalasetti; William James Walker
- Web page: https://patentgrep.com/patent/US11443036B2

## CPC

- G06F 21/554: {involving event detection and direct action}
- G06F 1/263: {Arrangements for using multiple switchable power supplies, e.g. battery and AC (G06F1/30 takes precedence)}
- G06F 1/3206: Monitoring of events, devices or parameters that trigger a change in power modality
- G06F 1/3287: by switching off individual functional units in the computer system
- G06F 21/32: using biometric data, e.g. fingerprints, iris scans or voiceprints
- G06F 21/602: {Providing cryptographic facilities or services}
- G06N 3/0464: Convolutional networks [CNN, ConvNet]
- G06N 3/09: Supervised learning
- G06V 40/16: Human faces, e.g. facial parts, sketches or expressions
- G06V 40/161: {Detection; Localisation; Normalisation}
- G06V 40/172: {Classification, e.g. identification}
- G06F 1/24: Resetting means
- G06F 2221/034: Test or assess a computer or a system
- G06N 3/08: Learning methods
- Y02D 10/00: Energy efficient computing, e.g. low power processors, power management or thermal management
- Y02D 30/50: in wire-line communication networks, e.g. low power modes or reduced link rate
- G06F: ELECTRIC DIGITAL DATA PROCESSING (computer systems based on specific computational models G06N)
- G06N: COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06V: IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- Y02D: CLIMATE CHANGE MITIGATION TECHNOLOGIES IN INFORMATION AND COMMUNICATION TECHNOLOGIES [ICT], I.E. INFORMATION AND COMMUNICATION TECHNOLOGIES AIMING AT THE REDUCTION OF THEIR OWN ENERGY USE

## Abstract

In some examples, an apparatus includes a management controller for use in a computer system having a processing resource for executing an operating system (OS) of the computer system, the management controller being separate from the processing resource and to perform, based on operation of the management controller within a cryptographic boundary, management of components of the computer system, the management of components comprising power control of the computer system. The management controller is to receive sensor data, perform facial recognition based on the sensor data, and determine whether to initiate a security action responsive to the facial recognition.

## Claims

### Claim 1

An apparatus comprising:
a first baseboard management controller (BMC) for use in a computer system having a processing resource for executing an operating system (OS) of the computer system, the first BMC being separate from the processing resource and to:
perform, based on operation of the first BMC within a cryptographic boundary, management of components of the computer system, the management of components comprising power control of the computer system;
receive image sensor data from an image sensor;
perform facial recognition based on the image sensor data;
receive, at the first BMC from a second BMC, further sensor data acquired by the second BMC remotely located from the first BMC;
determine, based on the further sensor data acquired by the second BMC, whether a condition present at a location of the image sensor is also present at a further location;
receive additional sensor data from an additional sensor, the additional sensor data indicative of whether a cover of the computer system has been opened; and
initiate a security action with respect to the computer system responsive to the facial recognition, the determination from the further sensor data of whether the condition present at the location of the image sensor is also present at the further location, and determining from the additional sensor data that the cover of the computer system has been opened, wherein the security action comprises encrypting data communicated by the first BMC.

### Claim 2 (depends on 1)

The apparatus of claim 1, wherein the first BMC is to log information relating to access by a user of the computer system responsive to the facial recognition indicating that the user accessing the computer system is an approved user.

### Claim 3 (depends on 1)

The apparatus of claim 1, further comprising an auxiliary power source to supply power to the first BMC when power is removed from the computer system.

### Claim 4 (depends on 1)

The apparatus of claim 1, wherein the first BMC is to employ a neural network to perform the facial recognition.

### Claim 5 (depends on 4)

The apparatus of claim 4, wherein the neural network is to categorize a face in an image included in the image sensor data, and the first BMC is to compare parametric data describing the face to a repository containing information relating to faces of authorized or unauthorized users.

### Claim 6

A non-transitory machine-readable storage medium comprising instructions that upon execution cause a first baseboard management controller (BMC) to:
perform, based on operation of the first BMC within a cryptographic boundary, management of components of a computer system, the management of components comprising power control of the computer system, wherein the first BMC is separate from a processing resource of the computer system;
receive image data from an image sensor;
detect a face in the image data;
determine whether the detected face corresponds to an authorized user;
receive second sensor data from a second sensor, the second sensor data indicative of whether a cover of the computer system has been opened;
receive, at the first BMC from a second BMC, third sensor data acquired by the second BMC remotely located from the first BMC;
determine, based on the third sensor data acquired by the second BMC, whether a condition present at a location of the image sensor is also present at a further location; and
initiate a security action with respect to the computer system responsive to determining that the detected face does not correspond to an authorized user, determining from the second sensor data that the cover of the computer system has been opened, and the determination from the third sensor data of whether the condition present at the location of the image sensor is also present at the further location, wherein the security action comprises encrypting data communicated by the first BMC.

### Claim 7 (depends on 6)

The non-transitory machine-readable storage medium of claim 6, wherein the instructions upon execution cause the first BMC to employ a neural network to detect the face in the image data.

### Claim 8

A computer system comprising:
a processing resource;
an operating system executable on the processing resource;
a first baseboard management controller (BMC) separate from the processing resource, the first BMC to:
perform, based on operation of the first BMC within a cryptographic boundary, management of components of the computer system, the management of components comprising power control of the computer system;
receive image data from an image sensor;
perform facial recognition based on the image data;
receive second sensor data from a second sensor, the second sensor data indicative of whether a cover of the computer system has been opened;
receive, at the first BMC from a second BMC, third sensor data acquired by the second BMC remotely located from the first BMC;
determine, based on the third sensor data acquired by the second BMC, whether a condition present at a location of the image sensor is also present at a further location;
determine to initiate a security action responsive to the facial recognition, determining from the second sensor data that the cover of the computer system has been opened, and the determination from the third sensor data of whether the condition present at the location of the image sensor is also present at the further location; and
perform the security action comprising encrypting data communicated by the first BMC.

### Claim 9 (depends on 8)

The computer system of claim 8, wherein the facial recognition is based on use of a neural network that is to categorize a face in the image data, and wherein the first BMC is to:
compare parametric data describing the face to a repository containing information relating to faces of authorized or unauthorized users; and
initiate the security action responsive to the facial recognition indicating that a user accessing the computer system is not an approved user and is based on a security policy.

### Claim 10 (depends on 1)

The apparatus of claim 1, wherein the first BMC is to initiate the security action responsive to the facial recognition indicating that a user accessing the computer system is not an approved user.

### Claim 11 (depends on 10)

The apparatus of claim 10, wherein the first BMC is to initiate the security action according to a policy based on a condition associated with an attempted access of the computer system.

### Claim 12 (depends on 10)

The apparatus of claim 10, wherein the security action further comprises an action selected from among deactivating power to a portion of the computer system, quiescing data traffic on a communication channel, or destroying data.

### Claim 13 (depends on 1)

The apparatus of claim 1, wherein the further sensor data is from a further sensor selected from among a sensor to detect opening of a cover, an accelerometer, a light sensor, an audio sensor, a rotation sensor, or an environmental sensor.