System and methods for cybersecurity analysis using UEBA and network topology data and trigger-based network remediation
A system and method for network cybersecurity analysis that uses user and entity behavioral analysis combined with network topology information and trigger-based network remediation to provide improved cybersecurity. The system and method involve gathering network entity information, establishing baseline behaviors for each entity, and monitoring each entity for behavioral anomalies that might indicate cybersecurity concerns. Further, the system and method involve incorporating network topology information into the analysis by generating a model of the network, annotating the model with risk and criticality information for each entity in the model and with a vulnerability level between entities, and using the model to evaluate cybersecurity risks to the network. Triggers may be based on risks or anomalous behavior and associated with a remediation action executed on the network by a security mitigation engine. The system and method may also dynamically adjust monitoring characteristics based on trigger events.
1 . A system for cybersecurity analysis using user and entity behavioral analysis (UEBA) with trigger-based network remediation, comprising:
a computing device comprising a memory, a processor, and a plurality of programming instructions stored in the memory of, and operating on the processor of, the computing device, wherein the plurality of programming instructions, when operating on the processor, cause the computing device to:
maintain a directed graph in the memory of the computing device, wherein the directed graph represents one or more predefined or system-defined groups within a computing network, and wherein the directed graph comprises: a plurality of nodes representing entities of the computing network, and a plurality of edges representing a directional relationship between one or more of the entities of the computing network;
perform network segmentation to represent the entities of the computing network in the directed graph, wherein performing network segmentation comprises:
assigning one or more of the entities of the computing network to logical segments representing the pre-defined or system-defined groups based on one or more properties of the entities; and
representing all entities assigned to a respective logical segment as a single entity in the directed graph;
monitor activity of a plurality of the entities based on one or more monitoring characteristics, wherein the monitoring characteristics used to monitor the activity of the plurality of the entities are selected based on one or more of the assigned logical segments of the monitored entity;
establish behavioral baseline data for each of the monitored entities from the monitored activity over a defined period of time;
receive an indication of a trigger event;
adjust one or more of the monitoring characteristics for one or more of the monitored entities based on the trigger event;
identify anomalous behavior of an entity of the monitored entities by comparing the monitored activity for said monitored entity to the behavioral baseline data for said monitored entity; and
calculate a risk of the anomalous behavior using one or more edges of the directed graph to determine a relationship between said monitored entity and one or more of the logical segments and their assigned entities;
in response to receipt of the indication of the trigger event, use a machine-learning algorithm or a rules-based algorithm to determine a sequence of actions to perform on one or more of the entities based on the calculated risk and one or more of the assigned logical segments of said entities; and
automatically execute the determined sequence of actions on one or more of the entities.
2 . The system of claim 1 , wherein the characteristics of how the directed graph is maintained is based on the trigger event and the one or more monitoring characteristics.
3 . The system of claim 1 , wherein the trigger event is associated with a detected anomaly, a detected deviation, or a specific pattern that differs from the behavioral baseline data.
4 . The system of claim 1 , wherein the monitoring characteristics include an amount of monitoring, a level of monitoring, a time period of monitoring, or a type of monitoring.
5 . The system of claim 1 , wherein the plurality of programming instructions, when operating on the processor, further cause the computing device to:
upon execution of the determined sequence of actions:
monitor the computing network to determine an effect of the sequence of actions on the computing network;
update the sequence of actions based on the determined effect; and
automatically execute the updated sequence of actions on one or more of the entities.
6 . The system of claim 1 , wherein the determined sequence of actions includes a remediation action.
7 . The system of claim 1 , wherein the plurality of programming instructions, when operating on the processor, further cause the computing device to:
upon execution of the determined sequence of actions:
continue to monitor the activity of the plurality of the entities based on the adjusted monitoring characteristics; and
update the behavioral baseline data for each of the monitored entities from the monitored activity.
8 . The system of claim 1 further comprising:
reconfiguring one or more of the logical segments of the directed graph stored in the memory of the computing device based on the trigger event.
9 . The system of claim 1 , wherein the plurality of programming instructions, when operating on the processor, further cause the computing device to generate one or more scores for each of the monitored entities, wherein the one or more scores are associated with one or more nodes or edges of the directed graph.
10 . The system of claim 9 , wherein the trigger event is based on the one or more scores.
11 . A method for cybersecurity analysis using user and entity behavioral analysis (UEBA) with trigger-based network remediation, comprising the steps of:
maintain a directed graph in a memory of a computing device, wherein the directed graph represents one or more predefined or system-defined groups within a computing network, and wherein the directed graph comprises: a plurality of nodes representing entities of the computing network, and a plurality of edges representing a directional relationship between one or more of the entities of the computing network;
performing network segmentation to represent the entities of the computing network in the directed graph, wherein performing network segmentation comprises:
assigning one or more of the entities of the computing network to logical segments representing the pre-defined or system-defined groups based on one or more properties of the entities; and
representing all entities assigned to a respective logical segment as a single entity in the directed graph;
monitoring activity of a plurality of the entities based on one or more monitoring characteristics, wherein the monitoring characteristics used to monitor the activity of the plurality of the entities are selected based on one or more of the assigned logical segments of the monitored entity;
establishing behavioral baseline data for each of the monitored entities from the monitored activity over a defined period of time;
receiving an indication of a trigger event;
adjusting one or more of the monitoring characteristics for one or more of the monitored entities based on the trigger event;
identifying anomalous behavior of an entity of the monitored entities by comparing the monitored activity for said monitored entity to the behavioral baseline data for said monitored entity; and
calculating a risk of the anomalous behavior using one or more edges of the directed graph to determine a relationship between said monitored entity and one or more of the logical segments and their assigned entities;
in response to receipt of the indication of the trigger event, using a machine-learning algorithm or a rules-based algorithm to determine a sequence of actions to perform on one or more of the entities based on the calculated risk and one or more of the assigned logical segments of said entities; and
automatically executing the determined sequence of actions on one or more of the entities.
12 . The method of claim 11 , wherein the characteristics of how the directed graph is maintained is based on the trigger event and the one or more monitoring characteristics.
13 . The method of claim 11 , wherein the trigger event is associated with a detected anomaly, a detected deviation, or a specific pattern that differs from the behavioral baseline data.
14 . The method of claim 11 , wherein the monitoring characteristics include an amount of monitoring, a level of monitoring, a time period of monitoring, or a type of monitoring.
15 . The method of claim 12 , further comprising the steps of:
upon execution of the determined sequence of actions:
monitoring the computing network to determine an effect of the sequence of actions on the computing network;
updating the sequence of actions based on the determined effect; and
automatically executing the updated sequence of actions on one or more of the entities.
16 . The method of claim 11 , wherein the determined sequence of actions includes a remediation action.
17 . The method of claim 11 , further comprising the steps of:
upon execution of the determined sequence of actions:
continuing to monitor the activity of the plurality of the entities based on the adjusted monitoring characteristics; and
updating the behavioral baseline data for each of the monitored entities from the monitored activity.
18 . The method of claim 11 further comprising the step of:
reconfiguring one or more of the logical segments of the directed graph stored in the memory of a computing device based on the trigger event.
19 . The method of claim 11 , further comprising the step of generating one or more scores for each of the monitored entities, wherein the one or more scores are associated with one or more nodes or edges of the directed graph.
20 . The method of claim 19 , wherein the trigger event is based on the one or more scores.