Classifying applications or activities based on network behavior
Embodiments are directed to monitoring network traffic in a network. A network monitoring engine may be employed to monitor the network to provide metric profiles based on a plurality of characteristics associated with one or more network flows. The network monitoring engine may provide profile objects based on the metric profiles. The network monitoring engine may provide the profile objects to a classifier engine. The classifier engine provide trained activity models selected from a plurality of trained activity models that may be based on a ranked ordering of characteristics of the trained activity models and the profile objects. The classifier engine may provide classification results for the profile objects based on the trained activity models. And, the network monitoring engine may execute policies based on the classification results associated with the profile objects.
1. A network computer for monitoring network traffic in a network, comprising:
a transceiver that communicates over the network;
a memory that stores at least instructions; and
one or more processors that execute instructions to perform actions, comprising:
employing a network monitoring engine to perform further actions, including:
monitoring the network to provide one or more metric profiles based on a plurality of characteristics associated with one or more network flows;
providing one or more profile objects based on the one or more metric profiles; and
providing the one or more profile objects to a classifier engine; and
employing the classifier engine to perform further actions, including:
providing one or more trained activity models selected from a plurality of trained activity models that are based on a ranked ordering of one or more characteristics of the one or more trained activity models and the one or more profile objects; and
providing one or more classification results for the one or more profile objects based on the one or more trained activity models; and
employing the network monitoring engine to execute one or more policies based on the one or more classification results associated with the one or more profile object.
2. The network computer of claim 1 , further comprising:
providing one or more labeled profile objects and one or more untrained activity models to a training engine; and
employing the training engine to perform further actions, including:
training the one or more untrained activity models based on the one or more labeled profile objects and one or more characteristics of the one or more untrained activity models; and
providing the one or more newly trained activity models to the classifier engine, wherein the one or more newly trained activity models are employed by the classifier engine to classify the one or more profile objects.
3. The network computer of claim 1 , wherein providing the one or more profile objects based on the one or more metric profiles, further comprises:
selecting two or more metric profiles that are associated with a same activity; and
providing one or more of the one or more profile objects based on the two or more metric profiles.
4. The network computer of claim 1 , wherein providing the one or more profile objects further comprises, discovering one or more metrics that correspond to a network entity in the monitored network based on the characteristics of the one or more network flows, wherein these characteristics are separate from process characteristics associated with the entity.
5. The network computer of claim 1 , further comprising:
providing the one or more classification results to one or more of another computer, a system, a client, or a remote service; and
employing the one or more of the other computer, the system, the client or the service to perform one or more other actions relevant to the one or more classification results, wherein the other actions include one or more of providing notification messages, providing events, creating log entries, raising user-interface alarms, or raising other alarms.
6. The network computer of claim 1 , further comprising, employing the network monitoring engine to provide one or more other profile objects that represent devices on the network, including, one or more of network computers, routers, switches, desktop computers, virtual devices, virtualized components, virtual networks, containers, mobile computers, smart phones, or Internet-of-Things (IoT) devices.
7. The network computer of claim 1 , wherein providing the one or more classification results for the one or more profile objects, further comprises, identifying one or more malicious processes or applications based on one or more characteristics of the one or more network flows, wherein these characteristics are collected remotely from process characteristics associated with a host that is executing the one or more malicious processes or applications.
8. The network computer of claim 1 , further comprising, employing the network monitoring engine to update one or more existing profile objects based on further monitoring of the one or more network flows or monitoring of one or more new network flows.
9. A system for monitoring network traffic in a network:
one or more network monitoring computers (NMCs), comprising:
a transceiver that communicates over the network;
a memory that stores at least instructions; and
one or more processors that execute instructions that perform actions, including:
employing a network monitoring engine to perform further actions, including:
monitoring the network to provide one or more metric profiles based on a plurality of characteristics associated with one or more network flows;
providing one or more profile objects based on the one or more metric profiles; and
providing the one or more profile objects to a classifier engine; and
employing the classifier engine to perform further actions, including:
providing one or more trained activity models selected from a plurality of trained activity models that are based on a ranked ordering of one or more characteristics of the one or more trained activity models and the one or more profile objects; and
providing one or more classification results for the one or more profile objects based on the one or more trained activity models; and
employing the network monitoring engine to execute one or more policies based on the one or more classification results associated with the one or more profile objects; and
one or more client computers, comprising:
a transceiver that communicates over the network;
a memory that stores at least instructions; and
one or more processors that execute instructions that perform actions, including:
providing one or more portions of the one or more network flows.
10. The system of claim 9 , further comprising:
providing one or more labeled profile objects and one or more untrained activity models to a training engine; and
employing the training engine to perform further actions, including:
training the one or more untrained activity models based on the one or more labeled profile objects and one or more characteristics of the one or more untrained activity models; and
providing the one or more newly trained activity models to the classifier engine, wherein the one or more newly trained activity models are employed by the classifier engine to classify the one or more profile objects.
11. The system of claim 9 , wherein providing the one or more profile objects based on the one or more metric profiles, further comprises:
selecting two or more metric profiles that are associated with a same activity; and
providing one or more of the one or more profile objects based on the two or more metric profiles.
12. The system of claim 9 , wherein providing the one or more profile objects further comprises, discovering one or more metrics that correspond to a network entity in the monitored network based on the characteristics of the one or more network flows, wherein these characteristics are separate from process characteristics associated with the entity.
13. The system of claim 9 , further comprising:
providing the one or more classification results to one or more of another computer, a system, a client, or a remote service; and
employing the one or more of the other computer, the system, the client or the service to perform one or more other actions relevant to the one or more classification results, wherein the other actions include one or more of providing notification messages, providing events, creating log entries, raising user-interface alarms, or raising other alarms.
14. The system of claim 9 , further comprising, employing the network monitoring engine to provide one or more other profile objects that represent devices on the network, including, one or more of network computers, routers, switches, desktop computers, virtual devices, virtualized components, virtual networks, containers, mobile computers, smart phones, or Internet-of-Things (IoT) devices.
15. The system of claim 9 , wherein providing the one or more classification results for the one or more profile objects, further comprises, identifying one or more malicious processes or applications based on one or more characteristics of the one or more network flows, wherein these characteristics are collected remotely from process characteristics associated with a host that is executing the one or more malicious processes or applications.
16. The system of claim 9 , further comprising, employing the network monitoring engine to update one or more existing profile objects based on further monitoring of the one or more network flows or monitoring of one or more new network flows.
17. A processor readable non-transitory storage media that includes instructions for monitoring network traffic over a network between one or more computers, wherein execution of the instructions by one or more processors on one or more network monitoring computers (NMCs) performs actions, comprising:
employing a network monitoring engine to perform further actions, including:
monitoring the network to provide one or more metric profiles based on a plurality of characteristics associated with one or more network flows;
providing one or more profile objects based on the one or more metric profiles; and
providing the one or more profile objects to a classifier engine; and
employing the classifier engine to perform further actions, including:
providing one or more trained activity models selected from a plurality of trained activity models that are based on a ranked ordering of one or more characteristics of the one or more trained activity models and the one or more profile objects; and
providing one or more classification results for the one or more profile objects based on the one or more trained activity models; and
employing the network monitoring engine to execute one or more policies based on the one or more classification results associated with the one or more profile objects.
18. The media of claim 17 , further comprising:
providing one or more labeled profile objects and one or more untrained activity models to a training engine; and
employing the training engine to perform further actions, including:
training the one or more untrained activity models based on the one or more labeled profile objects and one or more characteristics of the one or more untrained activity models; and
providing the one or more newly trained activity models to the classifier engine, wherein the one or more newly trained activity models are employed by the classifier engine to classify the one or more profile objects.
19. The media of claim 17 , wherein providing the one or more profile objects based on the one or more metric profiles, further comprises:
selecting two or more metric profiles that are associated with a same activity; and
providing one or more of the one or more profile objects based on the two or more metric profiles.
20. The media of claim 17 , wherein providing the one or more profile objects further comprises, discovering one or more metrics that correspond to a network entity in the monitored network based on the characteristics of the one or more network flows, wherein these characteristics are separate from process characteristics associated with the entity.
21. The media of claim 17 , further comprising:
providing the one or more classification results to one or more of another computer, a system, a client, or a remote service; and
employing the one or more of the other computer, the system, the client or the service to perform one or more other actions relevant to the one or more classification results, wherein the other actions include one or more of providing notification messages, providing events, creating log entries, raising user-interface alarms, or raising other alarms.
22. The media of claim 17 , further comprising, employing the network monitoring engine to provide one or more other profile objects that represent devices on the network, including, one or more of network computers, routers, switches, desktop computers, virtual devices, virtualized components, virtual networks, containers, mobile computers, smart phones, or Internet-of-Things (IoT) devices.
23. The media of claim 17 , wherein providing the one or more classification results for the one or more profile objects, further comprises, identifying one or more malicious processes or applications based on one or more characteristics of the one or more network flows, wherein these characteristics are collected remotely from process characteristics associated with a host that is executing the one or more malicious processes or applications.
24. A network computer for monitoring communication over a network between one or more computers, comprising:
a transceiver that communicates over the network;
a memory that stores at least instructions; and
one or more processors that execute instructions that perform actions, including:
employing a network monitoring engine to perform further actions, including:
monitoring the network to provide one or more metric profiles based on a plurality of characteristics associated with one or more network flows;
providing one or more profile objects based on the one or more metric profiles; and
providing the one or more profile objects to a classifier engine; and
employing the classifier engine to perform further actions, including:
providing one or more trained activity models selected from a plurality of trained activity models that are based on a ranked ordering of one or more characteristics of the one or more trained activity models and the one or more profile objects; and
providing one or more classification results for the one or more profile objects based on the one or more trained activity models; and
employing the network monitoring engine to execute one or more policies based on the one or more classification results associated with the one or more profile objects.
25. The network computer of claim 24 , further comprising:
providing one or more labeled profile objects and one or more untrained activity models to a training engine; and
employing the training engine to perform further actions, including:
training the one or more untrained activity models based on the one or more labeled profile objects and one or more characteristics of the one or more untrained activity models; and
providing the one or more newly trained activity models to the classifier engine, wherein the one or more newly trained activity models are employed by the classifier engine to classify the one or more profile objects.
26. The network computer of claim 24 , wherein providing the one or more profile objects based on the one or more metric profiles, further comprises:
selecting two or more metric profiles that are associated with a same activity; and
providing one or more of the one or more profile objects based on the two or more metric profiles.
27. The network computer of claim 24 , wherein providing the one or more profile objects further comprises, discovering one or more metrics that correspond to a network entity in the monitored network based on the characteristics of the one or more network flows, wherein these characteristics are separate from process characteristics associated with the entity.
28. The network computer of claim 24 , further comprising:
providing the one or more classification results to one or more of another computer, a system, a client, or a remote service; and
employing the one or more of the other computer, the system, the client or the service to perform one or more other actions relevant to the one or more classification results, wherein the other actions include one or more of providing notification messages, providing events, creating log entries, raising user-interface alarms, or raising other alarms.
29. The network computer of claim 24 , further comprising, employing the network monitoring engine to provide one or more other profile objects that represent devices on the network, including, one or more of network computers, routers, switches, desktop computers, virtual devices, virtualized components, virtual networks, containers, mobile computers, smart phones, or Internet-of-Things (IoT) devices.
30. The network computer of claim 24 , wherein providing the one or more classification results for the one or more profile objects, further comprises, identifying one or more malicious processes or applications based on one or more characteristics of the one or more network flows, wherein these characteristics are collected remotely from process characteristics associated with a host that is executing the one or more malicious processes or applications.