Authenticating usage data for processing by machine learning models

Patent metadata

Field	Value
Publication number	US-12332989-B2
Application number	US-202217967220-A
Country	US
Kind code	B2
Filing date	Oct 17, 2022
Priority date	Oct 17, 2022
Publication date	Jun 17, 2025
Grant date	Jun 17, 2025

Abstract

Methods, apparatus, and processor-readable storage media for authenticating usage data for processing by machine learning models are provided herein. An example method includes receiving, by a machine learning application installed in a user space of an operating system of a user device, a message from a software component, wherein the software component is: configured to collect usage data associated with the user device; signed with using private key corresponding to a digital certificate by an application installed on the user device; and deployed in a kernel space of the operating system, and wherein the message comprises usage data signed using the private key; authenticating, by the machine learning application, the usage data based on a public key corresponding to the digital certificate; and processing, by the machine learning application in response to a result of the authenticating, at least a portion of the authenticated usage data.

First claim

What is claimed is:

1. A computer-implemented method comprising:
receiving, by at least one machine learning application installed in a user space of an operating system of a user device, a message from a software component, wherein the software component is: (i) configured to collect usage data associated with the user device, (ii) signed, by an application installed on the user device, using a private key corresponding to a digital certificate, and (iii) deployed in a kernel space of the operating system based at least in part on an evaluation of the digital certificate, and wherein the message comprises usage data collected by the software component signed using the private key corresponding to the digital certificate;
authenticating, by the at least one machine learning application, the usage data based at least in part on a public key corresponding to the digital certificate; and
processing, by the at least one machine learning application in response to a result of the authenticating, at least a portion of the authenticated usage data;
wherein the method is performed by at least one processing device comprising a processor coupled to a memory.

2. The computer-implemented method of claim 1 , wherein the authenticating is based at least in part on at least one of: one or more timestamps associated with the message and a message authentication code associated with the message.

3. The computer-implemented method of claim 1 , wherein the message is sent using a kernel-user space communication.

4. The computer-implemented method of claim 1 , wherein the software component is deployed as a virtual device driver in the kernel space.

5. The computer-implemented method of claim 1 , wherein the usage data comprises at least one of:
hardware usage data collected from one or more input-output registers associated with one or more hardware devices; and
software usage data collected from at least one of: one or more data structures corresponding to the kernel space and one or more application programming interfaces corresponding to the kernel space.

6. The computer-implemented method of claim 1 , wherein the digital certificate is stored in a certificate database of the operating system.

7. The computer-implemented method of claim 1 , wherein the public key is obtained from the operating system.

8. The computer-implemented method of claim 1 , comprising:
initiating one or more automated adjustments to one or more settings associated with the user device based on one or more outputs that are generated by the processing the at least the portion of the authenticated usage data.

9. The computer-implemented method of claim 1 , wherein the digital certificate comprises a root certificate, and wherein the application is preinstalled on the user device with the root certificate.

10. A non-transitory processor-readable storage medium having stored therein program code of one or more software programs, wherein the program code when executed by at least one processing device causes the at least one processing device:
to receive, by at least one machine learning application installed in a user space of an operating system of a user device, a message from a software component, wherein the software component is: (i) configured to collect usage data associated with the user device, (ii) signed, by an application installed on the user device, using a private key corresponding to a digital certificate, and (iii) deployed in a kernel space of the operating system based at least in part on an evaluation of the digital certificate, and wherein the message comprises usage data collected by the software component signed using the private key corresponding to the digital certificate;
to authenticate, by the at least one machine learning application, the usage data based at least in part on a public key corresponding to the digital certificate; and
to process, by the at least one machine learning application in response to a result of the authenticating, at least a portion of the authenticated usage data.

11. The non-transitory processor-readable storage medium of claim 10 , wherein the authenticating is based at least in part on at least one of: one or more timestamps associated with the message and a message authentication code associated with the message.

12. The non-transitory processor-readable storage medium of claim 10 , wherein the message is sent using a kernel-user space communication.

13. The non-transitory processor-readable storage medium of claim 10 , wherein the software component is deployed as a virtual device driver in the kernel space.

14. The non-transitory processor-readable storage medium of claim 10 , wherein the usage data comprises at least one of:
hardware usage data collected from one or more input-output registers associated with one or more hardware devices; and
software usage data collected from at least one of: one or more data structures corresponding to the kernel space and one or more application programming interfaces corresponding to the kernel space.

15. The non-transitory processor-readable storage medium of claim 10 , wherein the digital certificate is stored in a certificate database of the operating system.

16. An apparatus comprising:
at least one processing device comprising a processor coupled to a memory;
the at least one processing device being configured:
to receive, by at least one machine learning application installed in a user space of an operating system of a user device, a message from a software component, wherein the software component is: (i) configured to collect usage data associated with the user device, (ii) signed, by an application installed on the user device, using a private key corresponding to a digital certificate, and (iii) deployed in a kernel space of the operating system based at least in part on an evaluation of the digital certificate, and wherein the message comprises usage data collected by the software component signed using the private key corresponding to the digital certificate;
to authenticate, by the at least one machine learning application, the usage data based at least in part on a public key corresponding to the digital certificate; and
to process, by the at least one machine learning application in response to a result of the authenticating, at least a portion of the authenticated usage data.

17. The apparatus of claim 16 , wherein the authenticating is based at least in part on at least one of: one or more timestamps associated with the message and a message authentication code associated with the message.

18. The apparatus of claim 16 , wherein the message is sent using a kernel-user space communication.

19. The apparatus of claim 16 , wherein the software component is deployed as a virtual device driver in the kernel space.

20. The apparatus of claim 16 , wherein the usage data comprises at least one of:
hardware usage data collected from one or more input-output registers associated with one or more hardware devices; and
software usage data collected from at least one of: one or more data structures corresponding to the kernel space and one or more application programming interfaces corresponding to the kernel space.

Assignees

• Dell Products Lp

Inventors

• Liu Jinpeng
• Chen Tianxiang
• Evans Sarah
• Jia Zhen

Classifications

• G06F21/33 Primary

  using certificates · CPC title