IP Library Granted Patent US 11,729,219
Granted Patent B2
US 11,729,219 · App. 17/228,547 · Granted Aug 15, 2023

Cloud security system implementing service action categorization

Inventors: Sandeep Chandana (Fremont, CA); Sekhar Sarukkai (Cupertino, CA)
Assignee: Skyhigh Security LLC
H04L63/20H04L63/1425H04L63/205
View Patent ↗
Loading inventors, assignments & file history…
Monitor This Case
Get email alerts when status or documents change.
Order Certified Copies
Most orders are placed with the USPTO same day — all within 24 business hours.
Order via The Patent Place →
Pre-filled with this patent's details
Quick Facts
Patent No.
US 11,729,219
App. No.
17/228,547
Granted
Aug 15, 2023
Kind
B2
Abstract

A service action category based cloud security system and method implement cloud security by categorizing service actions of cloud service providers into a set of service action categories. The service action categorization is performed agnostic to the applications or functions provided by the cloud service providers and also agnostic to the cloud service providers. With the service actions of cloud service providers thus categorized, cloud security monitoring and threat detection can be performed based on service action categories. Thus, cloud security can be implemented without requiring knowledge of the applications supported by the cloud service providers and without knowing all of the individual service actions supported by the cloud service providers.

Claims (68)

1. A method of implementing cloud security in an enterprise, the method comprising:

accessing, using a hardware processor, mapping data for service actions to a first set of service action categories, wherein each of the first set of service action categories describes a permitted and intended function that is performed by each of a plurality of service actions in the service action category;

identifying, using the processor, an uncategorized service action associated with a first cloud service provider in cloud activity data associated with the enterprise;

performing, using the processor, categorization of the uncategorized service action using at least one contextual categorization prediction method to map the uncategorized service action to a service action category in the first set of service action categories;

evaluating cloud security risk of cloud activities based on the first set of service action categories;

updating the mapping data with the service action category of the uncategorized service action;

detecting cloud security threats using the first set of service action categories; and

applying a security enforcement policy to cloud activities of the enterprise based on the first set of service action categories.

2. The method of claim 1 , wherein performing, using the processor, categorization of the uncategorized service action using at least one contextual categorization prediction method to map the uncategorized service action to a service action category in the first set of service action categories comprises:

performing categorization of the uncategorized service action by identifying a role of a user associated with the uncategorized service action.

3. The method of claim 2 , wherein performing categorization of the uncategorized service action by identifying a role of the user associated with the uncategorized service action comprises:

performing categorization of the uncategorized service action by identifying a role of the user within the enterprise and evaluating the cloud activity of the user around the time of the uncategorized service action.

4. The method of claim 2 , wherein performing categorization of the uncategorized service action by identifying a role of the user associated with the uncategorized service action comprises:

performing categorization of the uncategorized service action by identifying a job title or a job function of the user within the enterprise.

5. The method of claim 1 , wherein performing, using the processor, categorization of the uncategorized service action using at least one contextual categorization prediction method to map the uncategorized service action to a service action category in the first set of service action categories comprises:

performing categorization of the uncategorized service action by identifying an intent and sequence of a connection session containing the uncategorized service action.

6. The method of claim 5 , wherein performing categorization of the uncategorized service action by identifying an intent and sequence of a connection session containing the uncategorized service action comprises:

evaluating the sequence of service actions within the connection session including the uncategorized service action;

identifying service actions with previously mapped service action categories; and

generating a predicted service action category for the uncategorized service action based on the previously mapped service action categories for the service actions within the connection session.

7. The method of claim 5 , wherein performing categorization of the uncategorized service action by identifying an intent and sequence of a connection session containing the uncategorized service action comprises:

evaluating the sequence of service actions within the connection session including the uncategorized service action;

identifying a signature of service actions in the sequence of service actions; and

generating a predicted service action category for the uncategorized service action based on the signature of service actions.

8. The method of claim 1 , wherein performing, using the processor, categorization of the uncategorized service action using at least one contextual categorization prediction method to map the uncategorized service action to a service action category in the first set of service action categories, comprises:

transforming using the processor a name of the uncategorized service action into a core phrase;

dividing the core phrase into core words;

analyzing the core words using the contextual categorization prediction method to generate a plurality of predicted category labels for the uncategorized service action, each predicted category label being associated with a confidence estimate;

determining a weight to apply to each of the plurality of predicted category labels, the weight increasing or decreasing the confidence estimate for each of the plurality of predicted category labels; and

selecting the service action category to map to the uncategorized service action from the plurality of predicted category labels based on the confidence estimates.

9. The method of claim 8 , wherein determining a weight to apply to each of the plurality of predicted category labels, the weight increasing or decreasing the confidence estimate for each of the plurality of predicted category labels comprises:

determining the weight for each predicted category label using one or more weighing methods selected from subject matter expert assigned weights, training data based weights, and inverse confidence weights.

10. The method of claim 8 , wherein selecting the service action category to map to the uncategorized service action from the plurality of predicted category labels based on the confidence estimates comprises:

selecting the predicted category label with the highest confidence estimate as the service action category to map to the uncategorized service action.

11. A system for implementing cloud security for an enterprise, the system comprising:

a memory; and

a hardware processor in communication with the memory, the processor being programmed to:

access mapping data for service actions to a first set of service action categories, wherein each of the first set of service action categories describes a permitted and intended function that is performed by each of a plurality of service actions in the service action category;

identify an uncategorized service action associated with a first cloud service provider in cloud activity data associated with the enterprise;

perform categorization of the uncategorized service action using at least one contextual categorization prediction method to map the uncategorized service action to a service action category in the first set of service action categories;

evaluate cloud security risk of cloud activities based on the first set of service action categories;

update the mapping data with the service action category of the uncategorized service action;

detect cloud security threats using the first set of service action categories; and

apply a security enforcement policy to cloud activities of the enterprise based on the first set of service action categories.

12. The system recited in claim 11 , wherein the processor is further programmed to:

perform categorization of the uncategorized service action by identifying a role of a user associated with the uncategorized service action.

13. The system recited in claim 12 , wherein the processor is further programmed to:

perform categorization of the uncategorized service action by identifying a role of the user within the enterprise and evaluating the cloud activity of the user around the time of the uncategorized service action.

14. The system recited in claim 12 , wherein the processor is further programmed to:

perform categorization of the uncategorized service action by identifying a job title or a job function of the user within the enterprise.

15. The system recited in claim 11 , wherein the processor is further programmed to:

perform categorization of the uncategorized service action by identifying an intent and sequence of a connection session containing the uncategorized service action.

16. The system recited in claim 15 , wherein the processor is further programmed to:

evaluate the sequence of service actions within the connection session including the uncategorized service action;

identify service actions with previously mapped service action categories; and

generate a predicted service action category for the uncategorized service action based on the previously mapped service action categories for the service actions within the connection session.

17. The system recited in claim 15 , wherein the processor is further programmed to:

evaluate the sequence of service actions within the connection session including the uncategorized service action;

identify a signature of service actions in the sequence of service actions; and

generate a predicted service action category for the uncategorized service action based on the signature of service actions.

18. A non-transitory computer-readable medium containing computer executable instructions that, when executed by a processor, cause the processor to perform a method for implementing cloud security in an enterprise, the method comprising:

accessing mapping data for service actions to a first set of service action categories, wherein each of the first set of service action categories describes a permitted and intended function that is performed by each of a plurality of service actions in the service action category;

identifying an uncategorized service action associated with a first cloud service provider in cloud activity data associated with the enterprise;

performing categorization of the uncategorized service action using at least one contextual categorization prediction method to map the uncategorized service action to a service action category in the first set of service action categories;

evaluating cloud security risk of cloud activities based on the first set of service action categories;

updating the mapping data with the service action category of the uncategorized service action;

detecting cloud security threats using the first set of service action categories; and

applying a security enforcement policy to cloud activities of the enterprise based on the first set of service action categories.

Assignments (13)
ASSIGNMENT OF INTERCOMPANY FIRST LIEN PATENT SECURITY AGREEMENT Recorded Apr 14, 2025
From: UBS AG, STAMFORD BRANCH
To: ACQUIOM AGENCY SERVICES LLC
Reel/Frame 070840/0598 →
INTERCOMPANY FIRST LIEN PATENT SECURITY AGREEMENT Recorded Jan 24, 2025
From: SKYHIGH SECURITY LLC
To: UBS AG, STAMFORD BRANCH, AS COLLATERAL AGENT
Reel/Frame 070618/0001 →
RELEASE OF SECURITY INTEREST Recorded Oct 28, 2024
From: UBS AG, STAMFORD BRANCH, AS COLLATERAL AGENT
To: SKYHIGH SECURITY LLC
Reel/Frame 069272/0570 →
RELEASE OF SECURITY INTEREST Recorded Aug 16, 2024
From: STG PARTNERS, LLC
To: MUSARUBRA US LLC; SKYHIGH SECURITY LLC
Reel/Frame 068671/0435 →
FIRST LIEN PATENT SECURITY AGREEMENT Recorded Aug 15, 2024
From: MAGENTA SECURITY HOLDINGS LLC; SKYHIGH SECURITY LLC
To: UBS AG, STAMFORD BRANCH, AS COLLATERAL AGENT
Reel/Frame 068657/0666 →
SECURITY INTEREST Recorded Aug 1, 2024
From: MUSARUBRA US LLC; SKYHIGH SECURITY LLC
To: STG PARTNERS, LLC
Reel/Frame 068324/0731 →
NOTICE OF RELEASE OF SECURITY INTEREST IN PATENT Recorded Jun 9, 2022
From: JPMORGAN CHASE BANK, N.A.
To: MCAFEE, LLC
Reel/Frame 060317/0071 →
CHANGE OF NAME Recorded May 9, 2022
From: SKYHIGH NETWORKS, LLC
To: SKYHIGH SECURITY LLC
Reel/Frame 059912/0601 →
CHANGE OF NAME Recorded May 4, 2022
From: SKYHIGH NETWORKS, INC.
To: SKYHIGH NETWORKS, LLC
Reel/Frame 059855/0852 →
ASSIGNMENT OF ASSIGNOR'S INTEREST Recorded Apr 28, 2022
From: CHANDANA, SANDEEP; SARUKKAI, SEKHAR
To: SKYHIGH NETWORKS, INC.
Reel/Frame 059762/0801 →
SECURITY INTEREST Recorded Mar 3, 2022
From: MCAFEE, LLC
To: JPMORGAN CHASE BANK, N.A., AS ADMINISTRATIVE AGENT AND COLLATERAL AGENT
Reel/Frame 059354/0335 →
SECOND LIEN PATENT SECURITY AGREEMENT Recorded Jul 27, 2021
From: MUSARUBRA US LLC; SKYHIGH NETWORKS, LLC
To: UBS AG, STAMFORD BRANCH, AS COLLATERAL AGENT
Reel/Frame 056990/0960 →
FIRST LIEN PATENT SECURITY AGREEMENT Recorded Jul 27, 2021
From: MUSARUBRA US LLC; SKYHIGH NETWORKS, LLC
To: UBS AG, STAMFORD BRANCH, AS COLLATERAL AGENT
Reel/Frame 057453/0053 →
Continuity (2)
Continuation 15789658 · Oct 20, 2017
Related Publication 20210234902A1 · Jul 29, 2021
Cited By (1)
US 12,271,385