Similarity based approach for clustering and accelerating multiple incidents investigation
Systems, methods, and apparatuses are provided for clustering incidents in a computing environment. An incident notification relating to an event (e.g., a potential cyberthreat or any other alert) in the computing environment is received and a set of features may be generated based on the incident notification. The set of features may be provided as an input to a machine-learning engine to identify a similar incident notification in the computing environment. The similar incident notification may include a resolved incident notification or an unresolved incident notification. An action to resolve the incident notification may be received, and the received action may thereby be executed. In some implementations, in addition to resolving the received incident notification, the action may be executed to resolve a similar unresolved incident notification identified by the machine-learning engine.
1. A system for clustering incidents, comprising:
at least one processor circuit; and
a memory that stores program code configured to be executed by the at least one processor circuit, the program code comprising:
a featurizer configured to:
receive an incident notification, the incident notification relating to an event occurring in a computing environment; and
generate a feature set based on the incident notification, the feature set including an environmental feature extracted from a data feed separate from the incident notification and corresponding to the computing environment;
a machine-learning engine configured to apply a machine-learning-based model to identify a similar incident notification in the computing environment based on the feature set; and
an action resolver configured to:
receive an action to resolve at least one of the incident notification and the similar incident notification; and
execute the action.
2. The system of claim 1 , wherein the machine-learning-based model is configured to identify the similar incident notification based on a measure of similarity between the feature set of the incident notification and a feature set corresponding to the similar incident notification.
3. The system of claim 1 , wherein the similar incident notification comprises a similar resolved incident notification.
4. The system of claim 3 , wherein the machine-learning engine is configured to identify a corresponding action previously executed to resolve the similar resolved incident notification.
5. The system of claim 1 , wherein the similar incident notification comprises a similar unresolved incident notification.
6. The system of claim 5 , wherein the action resolver is configured to:
receive an indication that the similar unresolved incident notification should be resolved along with the incident notification; and
execute the action to resolve the incident notification and similar unresolved incident notification.
7. The system of claim 1 , wherein the feature set comprises a plurality of features, the plurality of features including a feature extracted from the incident notification; and
wherein the environmental feature extracted from the data feed separate from the incident notification is associated with at least one of a process creation, telemetry, a network, a hardware configuration, or a geo-location of the computing environment.
8. A method for resolving incidents, the method comprising:
receiving an incident notification, the incident notification relating to an event occurring in a computing environment;
generating a feature set based on the incident notification, the feature set including an environmental feature extracted from a data feed separate from the incident notification and corresponding to the computing environment;
providing the feature set as input to a machine-learning-based model that outputs a similar unresolved incident notification in the computing environment;
providing, for presentation in a user interface, information corresponding to the incident notification;
receiving, from the user interface, an action selected by a user to resolve the incident notification;
providing, for presentation in the user interface, an identification of the similar unresolved incident notification;
receiving, from the user interface, a selection of the similar unresolved incident notification to be resolved along with the incident notification; and
executing the action to resolve the incident notification and the similar unresolved incident notification.
9. The method of claim 8 , wherein the machine-learning-based model is configured to output the similar unresolved incident notification based on a measure of similarity between the feature set of the incident notification and a feature set corresponding to the similar unresolved incident notification.
10. The method of claim 8 , wherein the machine-learning-based model is further configured to output a similar resolved incident notification.
11. The method of claim 10 , further comprising:
providing, for presentation in the user interface, a corresponding action executed to resolve the similar resolved incident notification.
12. The method of claim 8 , further comprising:
providing, for presentation in the user interface, a reason indicating a similarity or a difference between the incident notification and the similar unresolved incident notification.
13. The method of claim 8 , further comprising:
providing, for presentation in the user interface, a measure of similarity between the incident notification and the similar unresolved incident notification.
14. The method of claim 8 , wherein the feature set comprises a plurality of features, the plurality of features including a feature extracted from the incident notification; and
wherein the environmental feature extracted from the data feed separate from the incident notification is associated with at least one of a process creation, telemetry, a network, a hardware configuration, or a geo-location of the computing environment.
15. A method for resolving incidents, the method comprising:
receiving an incident notification, the incident notification relating to an event occurring in a computing environment;
generating a feature set based on the incident notification, the feature set including an environmental feature extracted from a data feed separate from the incident notification and corresponding to the computing environment;
providing the feature set as input to a machine-learning-based model that outputs a similar resolved incident notification in the computing environment;
providing, for presentation in a user interface:
information corresponding to the incident notification;
an identification of the similar resolved incident notification; and
a reason indicating a similarity or a difference between the incident notification and the similar resolved incident notification; and
a corresponding action executed to resolve the similar resolved incident notification;
receiving, from the user interface, an action selected by a user to resolve the incident notification; and
executing the action to resolve the incident notification.
16. The method of claim 15 , wherein the machine-learning-based model is configured to output the similar resolved incident notification based on a measure of similarity between the feature set of the incident notification and a feature set corresponding to the similar resolved incident notification.
17. The method of claim 15 , wherein the machine-learning-based model is further configured to output a similar unresolved incident notification.
18. The method of claim 17 , further comprising:
receiving, from the user interface, an indication that the similar unresolved incident notification should be resolved along with the incident notification, and
executing the action to resolve the incident notification and the similar unresolved incident notification.
19. The method of claim 15 , further comprising:
providing, for presentation in the user interface, a measure of similarity between the incident and the similar resolved incident notification.
20. The method of claim 15 , wherein the feature set comprises a plurality of features, the plurality of features including a feature extracted from the incident notification; and
wherein the environmental feature extracted from the data feed separate from the incident notification is associated with at least one of a process creation, telemetry, a network, a hardware configuration, or a geo-location of the computing environment.