SYSTEM AND METHOD FOR MACHINE LEARNING APPLIED TO IN-BAND TO OUT-OF-BAND COMMUNICATIONS MANAGEMENT

• US 20200137688A1
• Filed: 10/31/2018
• Published: 04/30/2020
• Est. Priority Date: 10/31/2018
• Status: Active Grant

• Current Assignee: Dell Products LP (Dell Technologies Inc.)
• Original Assignee: Dell Products LP (Dell Technologies Inc.)
• Inventors: Gulbay, Sinem, Andrews, Carlton A.
• Granted Patent: US 10,939,380 B2
• Time in Patent Office: Days
• CPC Class Codes: H04W 12/08 Access security
• CPC Class Codes: H04W 12/121 Wireless intrusion detection systems [WIDS]; Wireless intrusion prevention systems [WIPS]
• CPC Class Codes: H04W 12/63 Location-dependent; Proximity-dependent
• CPC Class Codes: H04W 4/00 Services specially adapted for wireless communication networks; Facilities therefor
• CPC Class Codes: H04W 4/02 Services making use of location information
• CPC Class Codes: H04W 4/021 Services related to particular areas, e.g. point of interest [POI] services, venue services or geofences
• CPC Class Codes: H04W 4/029 Location-based management or tracking services
• CPC Class Codes: H04W 4/70 Services for machine-to-machine communication [M2M] or machine type communication [MTC]
• CPC Class Codes: H04W 48/04 based on user or terminal location or mobility data, e.g. moving direction, speed
• CPC Class Codes: H04W 52/0229 where the received signal is a wanted signal
• CPC Class Codes: H04W 52/0235 where the received signal is a power saving command
• CPC Class Codes: H04W 52/0251 using monitoring of local events, e.g. events related to user activity
• CPC Class Codes: H04W 52/0264 by selectively disabling software applications
• CPC Class Codes: H04W 64/00 Locating users or terminals or network equipment for network management purposes, e.g. mobility management
• CPC Class Codes: H04W 64/003 locating network equipment
• CPC Class Codes: Y02D 30/70 in wireless communication networks

Abstract

An information handling system operating a low power communications engine comprising a wireless adapter for communicating on a low power communication technology network for receiving low power communication technology data traffic for at least one always-on remote management service for the information handling system, a controller receiving a location status of the information handling system via the low power communication technology network indicating a location or network, where the controller executes code instructions for a low power communications engine to assess a location trust level from an environment characteristics analysis engine to determine whether the location status is a trusted zone location or an untrusted zone location utilizing binary classification machine learning based on input variables including data relating to history of activity at the location or on the network learned by the environment characteristics analysis engine from reported operational or network activity, and the controller to trigger an embedded controller to wake a BIOS of the information handling system and forward the incoming low power communication technology data traffic to in-band applications on the information handling system if the information handling system location status is determined to be in one trusted zone location and the controller to ignore the received low power communication technology data traffic if the information handling system location status is in one untrusted zone location

Claims

1. An information handling system comprising:

a wireless adapter for communicating on a low power communication technology network for receiving low power communication technology data traffic for at least one always-on remote management service for the information handling system;

a controller receiving a location status of the information handling system via the low power communication technology network indicating a location or network;

the controller executing code instructions for a low power communications engine to assess a location trust level from an environment characteristics analysis engine to determine whether the location status is a trusted zone location or an untrusted zone location utilizing classification machine learning based on input variables including data relating to history of activity at the location or on the network learned by the environment characteristics analysis engine from reported operational or network activity;

the controller to trigger an embedded controller to wake a BIOS of the information handling system and forward the incoming low power communication technology data traffic to in-band applications on the information handling system if the information handling system location status is determined to be in one trusted zone location; and

the controller to ignore the received low power communication technology data traffic if the information handling system location status is in one untrusted zone location.

2. The information handling system of claim 1 wherein the reported operational or network activity includes reports of security attacks reported on a network or at a location and secured or unsecured status of a wireless network at the location.

3. The information handling system of claim 1, further comprising:

the low power communications engine to store ignored low power communication technology data traffic in a memory until the information handling system has been awakened later from a sleep state; and

the low power communications engine to pass the low power communication technology data traffic to in-band applications on the information handling system.

4. The information handling system of claim 1 wherein the always-on remote management service includes a security service and alert messages pertaining to a security compromise are forwarded to the in-band application when the information handling system is in one untrusted zone location for immediate attention by the in-band application.

5. The information handling system of claim 1 wherein the reported operational or network activity includes reports of high-risk network activity by a user of the information handling activity.

6. The information handling system of claim 1, further comprising:

a memory operatively connected to the low power communications engine to store a database of location or network trust level grading based on learned environment characteristics from reports on history of activity at a plurality of locations or networks and further including reports on history of activity crowd-sourced from similar classes of devices as the information handling system.

7. The information handling system of claim 1, further comprising:

the low power communications engine accessing the environment characteristics analysis engine and database of location trust level grading at a remote agent via a low-power communication wireless link to determine if the information handling system is in one trusted zone location or not.

8. A computer implemented method comprising:

receiving low power communication technology network data traffic for at least one always-on remote management service for a managed information handling system via a wireless adapter operating via a low power communication technology network wireless link;

executing code instructions via a controller for a low power communications engine to assess a location trust level for a detected location of the managed information handling system from an environment characteristics analysis engine to determine if the information handling system is in a trusted zone location or an untrusted zone location based on history of activity at the detected location, wherein location trust levels for a plurality of locations are determined via binary classification machine learning based on a plurality of inputs of reported operational or network activity for that location received from the managed information handling system and crowd-sourced from a plurality of additional information handling systems having operated at the plurality of locations; and

triggering an embedded controller to wake a BIOS of the managed information handling system and forward the incoming low power communication technology data traffic to an in-band application on the managed information handling system if the managed information handling system is not in one trusted zone location to implement immediate security or management measures.

9. The method of claim 8, further comprising:

ignoring the received low power communication technology data traffic if the information handling system is in one trusted zone; and

storing ignored low power communication technology data traffic in a memory via the low power communications engine.

10. The method of claim 9, further comprising:

forwarding the low power communication technology data traffic stored in memory to the in-band application of the managed information handling system at a later time upon the next wake of the BIOS from a sleep state.

11. The method of claim 8 wherein the always-on remote management service includes a security service and alert messages pertaining to a security compromise are forwarded to the in-band application when the managed information handling system is not in one trusted zone location for immediate attention by the in-band application.

12. The method of claim 8 wherein the low power communication technology network utilizes a low power wide area network (LPWAN) protocol.

13. The method of claim 8 wherein the low power communication technology network utilizes a LoRa, Sigfox, or other low power IoT wireless protocol.

14. The method of claim 8 wherein the low power communications engine accesses database of location trust level grading at a remote agent of the environment characteristics analysis engine via a low-power communication wireless link to determine if the information handling system is in one trusted zone location or not.

15. The method of claim 8, wherein the environment characteristics analysis engine utilizes machine learning to designate the detected location as one untrusted zone location based a plurality of factors including reported levels of security attacks within a period of time, security of one or more wireless networks at the detected location, and the history of risky wireless data operations by the user.

16. An information handling system comprising:

a wireless adapter for communicating on a low power communication technology network for receiving and transmitting low power communication technology network data traffic for operating an always-on remote management service;

a remote management card executing code instructions via a controller for a low power communications engine to manage low power communication technology network data traffic;

the controller executing an environment characteristics analysis engine to employing classification machine learning to determine location trust levels for each location of a plurality of locations as a trusted zone location or an untrusted zone location for the information handling system, wherein the machine learning determines location trust levels from assessment of attacks on one or more networks at each location, number of alerts received for one or more networks at each location, security rating of one or more networks at each location, and encryption deployed for one or more networks at each location;

the low power communications engine to assess whether a detected location is a trusted zone location or an untrusted zone from the trust level provided by the environment characteristics analysis engine; and

the low power communications engine to determine whether to wake BIOS of the information handling system depending on whether the detected location is one trusted zone location or one untrusted zone location.

17. The information handling system of claim 16, further comprising:

the location trust levels adjusted such that determination of whether the detected location is trusted or untrusted depends further upon assessment of risky user behavior including program installation behavior, risky website visitation behavior, and SSID location of wireless activity raising additional basis for designation of the location as one untrusted zone location.

18. The information handling system of claim 16, further comprising:

the location trust levels adjusted such that determination of whether the detected location is trusted or untrusted depends further upon assessment of the security posture of the information handling system including sensitivity of enterprise data accessible by the information handling system and authentication levels required for access to the information handling system.

19. The information handling system of claim 16 wherein the low power communication technology network is a low power wide area network (LPWAN) protocol for LTE Category Narrow Band 1 (LTE NB-IoT) wireless links.

20. The information handling system of claim 16 wherein the low power communications engine and the environment characteristics analysis engine operate via an out-of-band operating system.