# US 12,737,493 B2 · Privacy protection for personal computing devices based on onlooker detection and classification

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

- Number: US 12,737,493 B2
- Document ID: US12737493B2
- Status: Granted
- Kind: B2
- Application number: 18/542,400
- Filed: 2023-12-15
- Published: 2025-06-19
- Granted: 2026-09-15
- Earliest claimed: 2023-12-15
- Assignees: Synaptics Incorporated
- Applicants: Synaptics Incorporated
- Inventors: Mohamed Ashraf Sheik-Nainar; Tomer Kimhi; Stuart Whitfield Hutson
- Web page: https://patentgrep.com/patent/US12737493B2

## CPC

- G06F 21/6245: {Protecting personal data, e.g. for financial or medical purposes}
- G06F 21/32: using biometric data, e.g. fingerprints, iris scans or voiceprints
- G06F 21/604: {Tools and structures for managing or administering access control systems}
- G06F 21/629: {to features or functions of an application}
- G06F 21/84: output devices, e.g. displays or monitors
- G06V 40/161: {Detection; Localisation; Normalisation}
- G06V 40/172: {Classification, e.g. identification}
- H04W 12/65: Environment-dependent, e.g. using captured environmental data
- G06F 21/62: Protecting access to data via a platform, e.g. using keys or access control rules
- G06N 20/00: Machine learning
- H04L 63/0861: {using biometrical features, e.g. fingerprint, retina-scan (cryptographic mechanisms or cryptographic arrangements for entity authentication using biological data H04L9/3231)}
- H04L 67/306: User profiles
- G06F: ELECTRIC DIGITAL DATA PROCESSING (computer systems based on specific computational models G06N)
- G06V: IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- H04W: WIRELESS COMMUNICATION NETWORKS (broadcast communication H04H; communication systems using wireless links for non-selective communication, e.g. wireless extensions H04M1/72)
- G06N: COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- H04L: TRANSMISSION OF DIGITAL INFORMATION, e.g. TELEGRAPHIC COMMUNICATION (arrangements common to telegraphic and telephonic communication H04M)

## Abstract

This disclosure provides methods, devices, and systems for protecting user privacy while operating a personal computing device. The present implementations more specifically relate to privacy protection techniques for personal computing devices based on onlooker detection and classification. In some aspects, a computing device may include a display, one or more sensors, and a privacy controller that receives sensor data from the one or more sensors and controls the display based on a presence or classification of onlookers associated with the received sensor data. In some implementations, the privacy controller may compare any onlookers detected from the sensor data to a database of contacts associated with the user and classify each onlooker as a “trusted onlooker” or “nontrusted onlooker” based on the comparison. More specifically, the privacy controller may selectively activate a privacy protection mechanism associated with the display based on whether a nontrusted onlooker is detected.

## Claims

### Claim 1

A method performed by a controller for a computing device, comprising:
receiving sensor data from one or more sensors associated with the computing device;
identifying an authorized user of the computing device based on the received sensor data;
detecting one or more objects of interest associated with the received sensor data, the one or more objects of interest including one or more unrecognized persons that are not identified as the authorized user;
extracting one or more features from the sensor data for each of the one or more unrecognized persons;
retrieving contact information from an address book managed by a phone or email client configured for the authorized user or from an organizational directory provided by an organization to which the authorized user belongs, wherein the contact information includes object recognition data for one or more contacts within the address book or organizational directory;
classifying each unrecognized person of the one or more unrecognized persons as a trusted onlooker or a nontrusted onlooker based on whether the one or more features extracted for the unrecognized person match the object recognition data; and
controlling a display associated with the computing device based on classifying each unrecognized person.

### Claim 2 (depends on 1)

The method of claim 1, wherein the object recognition data includes one or more images or voice recordings associated with the one or more contacts.

### Claim 3 (depends on 1)

The method of claim 1, wherein the controlling of the display comprises:
outputting a notification to the display responsive to determining that the one or more features for at least one unrecognized person of the one or more unrecognized persons do not match the object recognition data.

### Claim 4 (depends on 1)

The method of claim 1, further comprising:
determining a relationship between the authorized user and a first contact of the one or more contacts responsive to determining that the one or more features for at least one unrecognized person of the one or more unrecognized persons match the object recognition data associated with the first contact, the at least one unrecognized person being classified based at least in part on the relationship between the authorized user and the first contact.

### Claim 5 (depends on 4)

The method of claim 4, further comprising storing information indicating an organizational role or title associated with each contact of the one or more contacts in a database, the relationship between the authorized user and the first contact being determined based at least in part on the organizational role or title associated with the first contact.

### Claim 6 (depends on 4)

The method of claim 4, further comprising storing information indicating a history of communication between the authorized user and each contact of the one or more contacts in a database, the relationship between the authorized user and the first contact being determined based at least in part on the history of communication between the authorized user and the first contact.

### Claim 7 (depends on 4)

The method of claim 4, further comprising:
determining a type of content presented on the display, the at least one unrecognized person further being classified based at least in part on the type of content presented on the display.

### Claim 8 (depends on 7)

The method of claim 7, wherein the at least one unrecognized person is classified as a trusted onlooker for the type of content presented on the display responsive to determining that the relationship between the authorized user and the first contact satisfies a set of criteria associated with type of content.

### Claim 9 (depends on 7)

The method of claim 7, wherein the at least one unrecognized person is classified as a nontrusted onlooker for the type of content presented on the display responsive to determining that the relationship between the authorized user and the first contact does not satisfy a set of criteria associated with the type of content.

### Claim 10 (depends on 9)

The method of claim 9, wherein the controlling of the display comprises:
obfuscating the content presented on the display responsive to classifying at least one unrecognized person of the one or more unrecognized persons as a nontrusted onlooker for the type of content.

### Claim 11 (depends on 1)

The method of claim 1, wherein the authorized user is identified, the one or more objects are detected, and the one or more unrecognized persons are classified within a trusted execution environment (TEE) provided by an application-specific integrated circuit (ASIC) of the computing device.

### Claim 12 (depends on 11)

The method of claim 11, wherein:
the ASIC is separate from a central processor of the computing device that executes an operating system; and
the TEE prevents the sensor data from being accessed by software or hardware outside of the TEE.

### Claim 13 (depends on 1)

The method of claim 1, wherein;
at least one unrecognized person of the one or more unrecognized persons is classified as a trusted onlooker for first content displayed on the display that is associated with a first application;
the at least one unrecognized person is classified as a nontrusted onlooker for second content displayed on the display that is associated with a second application; and
the controlling of the display comprises:
refraining from obfuscating the first content; and
obfuscating the second content.

### Claim 14

A controller for a computing device, comprising:
a processing system; and
a memory storing instructions that, when executed by the processing system, causes the controller to:
receive sensor data from one or more sensors associated with the computing device;
identify an authorized user of the computing device based on the received sensor data;
detect one or more objects of interest associated with the received sensor data, the one or more objects of interest including one or more unrecognized persons that are not identified as the authorized user;
extract one or more features from the sensor data for each of the one or more unrecognized persons;
retrieve contact information from an address book managed by a phone or email client configured for the authorized user or from an organizational directory provided by an organization to which the authorized user belongs, wherein the contact information includes object recognition data for one or more contacts within the address book or organizational directory;
classify each unrecognized person of the one or more unrecognized persons as a trusted onlooker or a nontrusted onlooker on whether the one or more features extracted for the unrecognized person match the object recognition data; and
control a display associated with the computing device based on classifying each unrecognized person.

### Claim 15 (depends on 14)

The controller of claim 14, wherein execution of the instructions further causes the controller to:
determine a relationship between the authorized user and a first contact of the one or more contacts responsive to determining that the one or more features for at least one unrecognized person of the one or more unrecognized persons match the object recognition data associated with the first contact, the at least one unrecognized person being classified based at least in part on the relationship between the authorized user and the first contact.

### Claim 16 (depends on 15)

The controller of claim 15, further comprising storing information indicating an organizational role or title associated with each contact of the one or more contacts, the relationship between the authorized user and the first contact being determined based at least in part on the organizational role or title associated with the first contact.

### Claim 17 (depends on 15)

The controller of claim 15, further comprising storing information indicating a history of communication between the authorized user and each contact of the one or more contacts, the relationship between the authorized user and the first contact being determined based at least in part on the history of communication between the authorized user and the first contact.
