Systems and methods for multi-event correlation
Provided herein are systems and methods for multi-event correlation. Receiving a stream of events, each leaf rule engine may detect a plurality of events from the stream that matches a characteristic for the leaf rule engine. Each leaf rule engine may identify, from the plurality of events and within a time window, a group of events that satisfies a condition for the respective leaf rule engine. A root conditions engine may receive a stream of leaf events corresponding to the group of events identified by each leaf rule engine. The root conditions engine may identify, from the received stream of leaf events and within a root time window, a collection of events that satisfies a condition for the root conditions engine. A trigger may execute an action according to the collection of events identified within the root time window.
1. A system for multi-event correlation, comprising:
one or more processors coupled with memory, configured to:
receive, for a leaf rule, a stream of events each corresponding to an activity of at least one of a user, a device, or a program;
detect, from the stream of events, a first plurality of events in accordance with a filter of the leaf rule;
identify, from the first plurality of events, a second plurality of events satisfying a condition within a time window of the leaf rule; and
provide the second plurality of events to a root rule to identify a third plurality of events with which to execute an action in accordance with a trigger.
2. The system of claim 1 , wherein the one or more processors is further configured to modify at least one of the filter, the condition, or the time window of the leaf rule based at least on an administrative specification.
3. The system of claim 1 , wherein the one or more processors is further configured to set at least one of the filter, the condition, or the time window of the leaf rule using a machine learning model.
4. The system of claim 1 , wherein the one or more processors is further configured to shift the time window to apply the conditions to the first plurality of events.
5. The system of claim 1 , wherein the filter of the leaf rule defines a characteristic of events identified to be at least one of a potential anomaly, a risk, or a threat to detect the first plurality of events.
6. The system of claim 1 , wherein the condition of the leaf rule defines at least one of a total number of events, a total number of devices, a total number of files, or a total number of bytes accumulated within the time window to identify the second plurality of events.
7. The system of claim 1 , wherein at least one of the filter, the condition, or the time window of the leaf rule differs from a corresponding filter, condition, or time window of another leaf rule.
8. A system for multi-event correlation, comprising:
one or more processors coupled with memory, configured to:
receive, for a root rule, a stream of events identified by a leaf rule, each event of the stream of events corresponding to an activity at least one of a user, a device, or a program;
determine, from the stream of events, a first plurality of events within a time window of the root rule;
identify, from the first plurality of events within the time window, a second plurality of events satisfying a condition of the root rule; and
provide, to a trigger, the second plurality of events with which to execute an action.
9. The system of claim 8 , wherein the one or more processors is further configured to modify at least one of the filter, the condition, or the time window of the root rule based at least on an administrative specification.
10. The system of claim 8 , wherein the one or more processors is further configured to set at least one of the filter, the condition, or the time window of the root rule using a machine learning model.
11. The system of claim 8 , wherein the one or more processors is further configured to aggregate the stream of events identified from a plurality of leaf rules, each of the plurality of leaf rules identifying a corresponding subset of events in accordance with a respective filter, time window, and condition.
12. The system of claim 8 , wherein the time window of the root rule differs from a time window of the leaf rule to determine the first plurality of events from the stream of events.
13. The system of claim 8 , wherein the condition of the root rule defines at least one of a total number of events, a total number of devices, a total number of files, or a total number of bytes accumulated within the time window to identify the second plurality of events.
14. The system of claim 8 , wherein the action executed by the trigger includes at least one of: an initiation of an alarm for a potential anomaly, a risk, or threat; or a provision of an instruction to pause or terminate execution of the program.
15. A method of correlating across multiple events, comprising:
receiving, by a computing system, for a leaf rule, a stream of events each corresponding to an activity of at least one of a user, a device, or a program;
detecting, by the computing system, from the stream of events, a first plurality of events in accordance with a filter of the leaf rule;
identifying, by the computing system, from the first plurality of events, a second plurality of events satisfying a condition within a time window of the leaf rule; and
providing, by the computing system, the second plurality of events to a root rule to identify a third plurality of events.
16. The method of claim 15 , further comprising:
determining, by the computing system, from the second plurality of events, the third plurality of events within a time window of the root rule;
identifying, by the computing system, from the third plurality of events within the time window of the root rule, a fourth plurality of events satisfying a condition of the root rule; and
provide, to a trigger, the fourth plurality of events with which to execute an action.
17. The method of claim 16 , further comprising aggregating, by the computing system, the second plurality of events identified from a plurality of leaf rules, each of the plurality of leaf rules identifying a corresponding subset of events in accordance with a respective filter, time window, and condition.
18. The method of claim 16 , wherein the action executed by the trigger includes at least one of: an initiation of an alarm for a potential anomaly, a risk, or threat; or a provision of an instruction to pause or terminate execution of the program.
19. The method of claim 15 , wherein the filter of the leaf rule defines a characteristic of events identified to be at least one of a potential anomaly, a risk, or a threat to detect the first plurality of events.
20. The method of claim 15 , wherein the condition of the leaf rule defines at least one of a total number of events, a total number of devices, a total number of files, or a total number of bytes accumulated within the time window to identify the second plurality of events.