Using graph-based models to identify datacenter anomalies
Activities within a network environment are monitored (e.g., using agents). At least a portion of the monitored activities are used to generate a logical graph model. The generated logical graph model is used to determine an anomaly. The detected anomaly is recorded and can be used to generate an alert.
1. A system, comprising:
a processor configured to:
monitor activities within a network environment;
generate a multidimensional logical graph model comprising a set of nodes and a set of edges using at least a portion of the monitored activities; and
determine, using the generated logical graph model, an anomaly, and in response to detecting the anomaly, record the anomaly;
wherein a first node included in the set of nodes corresponds to an entity of a first type and wherein a second node included in the set of nodes corresponds to an entity of a second type that is different from the first type;
wherein the first node comprises a plurality of individual elements clustered together;
wherein a first edge connects the first node and the second node and wherein the first edge has a first edge type;
wherein a second edge connects the second node and a third node and wherein the second edge has a second edge type that is different from the first edge type; and
wherein the first edge type indicates a first type of behavioral relationship between arbitrary nodes interconnected by the first edge type and wherein the second edge type indicates a different type of behavioral relationship between two arbitrary nodes interconnected by the second edge type; and
a memory coupled to the processor and configured to provide the processor with instructions.
2. The system of claim 1 , wherein the graph comprises process information.
3. The system of claim 1 , wherein the generated logical graph model represents a baseline of behavior of nodes included in the network environment.
4. The system of claim 3 , wherein using the logical graph model to detect the anomaly includes comparing a current graph associated with the network environment against the baseline.
5. The system of claim 1 , wherein the network environment comprises a datacenter.
6. The system of claim 1 , wherein the detected anomaly is associated with identifying a security threat.
7. The system of claim 1 , wherein the logical graph model is generated at least in part by generating a graph of physical connection information.
8. The system of claim 1 , wherein the logical graph model is generated at least in part by performing a clustering operation.
9. The system of claim 8 , wherein clustering operation includes performing a Matching Neighbor clustering.
10. The system of claim 8 , wherein clustering operation includes performing a similarity clustering.
11. The system of claim 1 , wherein the logical graph model is generated at least in part by performing a split on a graph.
12. The system of claim 11 , wherein the split is based at least in part on an application type.
13. The system of claim 1 , wherein the processor is further configured to determine whether a process matches a predetermined application type included in a set of predetermined application types.
14. The system of claim 13 , wherein the processor is further configured to generate an alert in response to determining that the process does not match any members of the set of predetermined application types.
15. The system of claim 1 , wherein detecting the anomaly includes detecting a new node in the logical graph model.
16. The system of claim 1 , wherein detecting the anomaly includes detecting a new edge in the logical graph model.
17. A method, comprising:
monitoring activities within a network environment;
generating a multidimensional logical graph model comprising a set of nodes and a set of edges using at least a portion of the monitored activities; and
determining, using the generated logical graph model to detect an anomaly, and in response to detecting the anomaly, recording the anomaly;
wherein a first node included in the set of nodes corresponds to an entity of a first type and wherein a second node included in the set of nodes corresponds to an entity of a second type that is different from the first type;
wherein the first node comprises a plurality of individual elements clustered together;
wherein a first edge connects the first node and the second node and wherein the first edge has a first edge type;
wherein a second edge connects the second node and a third node and wherein the second edge has a second edge type that is different from the first edge type; and
wherein the first edge type indicates a first type of behavioral relationship between arbitrary nodes interconnected by the first edge type and wherein the second edge type indicates a different type of behavioral relationship between two arbitrary nodes interconnected by the second edge type.
18. The method of claim 17 , wherein the graph comprises process information.
19. The method of claim 17 , wherein the generated logical graph model represents a baseline of behavior of nodes included in the network environment.
20. The method of claim 19 , wherein using the logical graph model to detect the anomaly includes comparing a current graph associated with the network environment against the baseline.
21. The method of claim 17 , wherein the network environment comprises a datacenter.
22. The method of claim 17 , wherein the detected anomaly is associated with identifying a security threat.
23. The method of claim 17 , wherein the logical graph model is generated at least in part by generating a graph of physical connection information.
24. The method of claim 17 , wherein the logical graph model is generated at least in part by performing a clustering operation.
25. The method of claim 24 , wherein clustering operation includes performing a Matching Neighbor clustering.
26. The method of claim 24 , wherein clustering operation includes performing a similarity clustering.
27. The method of claim 17 , wherein the logical graph model is generated at least in part by performing a split on a graph.
28. The method of claim 27 , wherein the split is based at least in part on an application type.
29. The method of claim 17 , wherein the processor is further configured to determine whether a process matches a predetermined application type included in a set of predetermined application types.
30. The method of claim 29 , wherein the processor is further configured to generate an alert in response to determining that the process does not match any members of the set of predetermined application types.
31. The method of claim 17 , wherein detecting the anomaly includes detecting a new node in the logical graph model.
32. The method of claim 17 , wherein detecting the anomaly includes detecting a new edge in the logical graph model.
33. A computer program product embodied in a non-transitory computer readable storage medium and comprising computer instructions for:
monitoring activities within a network environment;
generating a multidimensional logical graph model comprising a set of nodes and a set of edges using at least a portion of the monitored activities; and
determining, using the generated logical graph model to detect an anomaly, and in response to detecting the anomaly, recording the anomaly;
wherein a first node included in the set of nodes corresponds to an entity of a first type and wherein a second node included in the set of nodes corresponds to an entity of a second type that is different from the first type;
wherein the first node comprises a plurality of individual elements clustered together;
wherein a first edge connects the first node and the second node and wherein the first edge has a first edge type;
wherein a second edge connects the second node and a third node and wherein the second edge has a second edge type that is different from the first edge type; and
wherein the first edge type indicates a first type of behavioral relationship between arbitrary nodes interconnected by the first edge type and wherein the second edge type indicates a different type of behavioral relationship between two arbitrary nodes interconnected by the second edge type.