Interface having selectable, interactive views for evaluating potential network compromise

Patent metadata

Field	Value
Publication number	US-9609011-B2
Application number	US-201514928563-A
Country	US
Kind code	B2
Filing date	Oct 30, 2015
Priority date	Aug 31, 2015
Publication date	Mar 28, 2017
Grant date	Mar 28, 2017

Abstract

A security platform employs a variety techniques and mechanisms to detect security related anomalies and threats in a computer network environment. The security platform is “big data” driven and employs machine learning to perform security analytics. The security platform performs user/entity behavioral analytics (UEBA) to detect the security related anomalies and threats, regardless of whether such anomalies/threats were previously known. The security platform can include both real-time and batch paths/modes for detecting anomalies and threats. By visually presenting analytical results scored with risk ratings and supporting evidence, the security platform enables network security administrators to respond to a detected anomaly or threat, and to take action promptly.

First claim

What is claimed is:

1. A computerized method comprising:
receiving event data associated with network activities by entities, wherein entities include devices, applications, and network users;
identifying instances of potential network compromise by applying machine learning models to the event data, wherein instances include threats and/or anomalies;
causing display, in a graphical user interface, of a user-selectable toggle to switch between a plurality of views, including at least one instances view comprising a listing of instances of potential network compromise and at least one entities view comprising a listing of the entities that participated in network activities that triggered determinations of potential network compromise, wherein each listed instance and entity is linked to a corresponding detailed view;
upon receiving, via the graphical user interface, a user's selection of an instance, causing the graphical user interface to generate a detailed view comprising (i) additional data about the selected instance, including data identifying each entity associated with the selected instance, (ii) a prompt to take an action in response to the instance, and a prompt to tag the selected instance for future tracking;
upon receiving, via the graphical user interface and in response to the prompt, a user's indication to take an action, providing feedback to a model training process thread to update the machine learning models for identifying future instances of potential network compromise; and
upon receiving a selection by a user of a tag, associating the tag with the selected instance such that the tag is included (i) in response to subsequent requests to generate the detailed view of the selected instance and (ii) in response to requests to generate the detailed view of a selected entity associated with the selected instance.

2. The method of claim 1 , wherein identified instances of potential network compromise include anomalies, and at least one instances view comprises an anomalies view listing each identified anomaly with its associated anomaly type and date that the anomaly occurred.

3. The method of claim 1 , wherein identified instances of potential network compromise include threats, and at least one instances view comprises a threat view listing each identified threat with its associated threat type and start date that the threat began.

4. The method of claim 1 , wherein at least one entities view provides a listing of devices, applications, and network users.

5. The method of claim 1 , wherein when the graphical user interface provides the detailed view comprising additional data about a selected instance, the user is prompted to designate whether the selected instance is a false positive, and
upon receiving a designation from the user that the selected instance is a false positive, associating the designation to be included in the additional data provided in response to subsequent requests to generate the detailed view of the selected instance.

6. The method of claim 1 , further comprising:
upon receiving, via the graphical user interface, a selection by a user of an entity, causing the graphical user interface to generate a detailed view comprising additional data about the selected entity, including data identifying each instance associated with the selected entity;
wherein when the graphical user interface provides the detailed view comprising additional data about the selected entity, the user is prompted to tag the selected entity for future tracking, and
upon receiving a selection by a user of a tag, associating the tag with the selected entity such that the tag is included in the additional data provided in response to subsequent requests for the detailed view of the selected entity.

7. The method of claim 1 , wherein when the identified instances of potential network compromise from the event data include threats, the instances view lists the identified threats and, for each entry in the listing, a threat type from a set including at least one of malware, data exfiltration, compromise of the organization's website, large file transfers, and attack.

8. The method of claim 1 , wherein when the identified instances of potential network compromise from the event data include anomalies, the instances view lists the identified anomalies and, for each entry in the listing, an anomaly type from a set including at least one of an alarm, an excessive data transfer, and an unusual login time.

9. The method of claim 1 , wherein when the identified instances of potential network compromise from the event data comprise threats, the additional data associated with the detailed view of a threat includes a graphical representation of a relationship between entities participating in the network activities that triggered detection of the threat.

10. The method of claim 1 , wherein when the identified instances of potential network compromise from the event data comprise anomalies, the additional data associated with the detailed view of an anomaly includes a graphical representation of a relationship between entities participating in the network activities that triggered detection of the anomaly.

11. The method of claim 1 , wherein when the identified instances of potential network compromise from the event data comprise threats, the detailed view of a threat prompts the user to designate whether the threat has been resolved.

12. The method of claim 1 , wherein the identified instances of potential network compromise from the event data comprise threats, and each threat is classified as a type from a set of threat types, the set of types including at least one type pertaining to external behavior or insider behavior relative to the computer network.

13. The method of claim 1 , wherein the indication received in response to the prompt is that the identified instance of potential network compromise is not a threat.

14. The method of claim 1 , wherein the action indicated by the user is at least one of stopping the intrusion, shutting down network access, locking out users, terminating file transfer, or shutting down software or hardware processes.

15. The method of claim 1 , wherein the additional data about the selected instance in the detailed view further includes the received event data that triggered identification of the instance.

16. A non-transitory, computer-readable storage medium storing instructions, an execution of which in a computer system causes the computer system to perform operations comprising:
receiving event data associated with network activities by entities, wherein entities include devices, applications, and network users;
identifying instances of potential network compromise by applying machine learning models to the event data, wherein instances include threats and/or anomalies;
causing display, in a graphical user interface, of a user-selectable toggle to switch between a plurality of views, including at least one instances view comprising a listing of instances of potential network compromise and at least one entities view comprising a listing of the entities that participated in network activities that triggered determinations of potential network compromise, wherein each listed instance and entity is linked to a corresponding detailed view;
upon receiving, via the graphical user interface, a user's selection of an instance, causing the graphical user interface to generate a detailed view comprising (i) additional data about the selected instance, including data identifying each entity associated with the selected instance, (ii) a prompt to take an action in respon

Assignees

• Splunk Inc

Inventors

• Muddu Sudhakar
• Tryfonas Christos

Classifications

• G06N20/20 Primary

  Ensemble learning · CPC title

• H04L63/1416

  Event detection, e.g. attack signature detection · CPC title

• G06N7/01

  Probabilistic graphical models, e.g. probabilistic networks · CPC title

• G06F40/134

  Hyperlinking · CPC title

• G06F16/254

  Extract, transform and load [ETL] procedures, e.g. ETL data flows in data warehouses · CPC title