ADAPTIVE ANOMALY CONTEXT DESCRIPTION
Techniques are disclosed for providing a context-aware description of anomalous behavior in a computer network. According to one embodiment of the present disclosure, a description of an anomaly detected in computer network activity is received. The description includes one or more features of the computer network associated with the anomaly. Contextual information relating to at least one of the features is generated based on a logical network topology. The logical network topology specifies a plurality of network traffic attributes of the computer network. An alert that includes a second description of the anomaly and the contextual information is generated.
1 . A computer-implemented method for providing a context-aware description of anomalous behavior in a computer network, the method comprising:
receiving a first description of an anomaly detected in computer network activity, wherein the first description includes one or more features of the computer network associated with the detected anomaly;
generating contextual information relating to at least one of the features based on a logical network topology, wherein the logical network topology specifies a plurality of network traffic attributes of the computer network; and
generating an alert that includes a second description of the anomaly and the contextual information relating to the features.
2 . The method of claim 1 , wherein the first description of the anomaly is a low-level description of the one or more features and wherein the second description of the anomaly is a human-readable description of the features that includes the contextual information.
3 . The method of claim 2 , further comprising:
translating the first description to the second description based on a mapping of at least a first feature of the one or more features to a corresponding component in the computer network.
4 . The method of claim 1 , further comprising:
presenting the alert via a user interface.
5 . The method of claim 1 , wherein the network traffic attributes include at least one of a connectivity pattern, frequency pattern, and an intensity pattern associated with a component in the computer network.
6 . The method of claim 1 , wherein the contextual information describes previously observed network traffic attributes associated with a component in the computer network.
7 . The method of claim 1 , wherein the anomaly is generated by a neuro-linguistic behavioral recognition system.
8 . A non-transitory computer-readable storage medium having instructions, which, when executed on a processor, performs an operation for providing a context-aware description of anomalous behavior in a computer network, comprising:
receiving a first description of an anomaly detected in computer network activity, wherein the first description includes one or more features of the computer network associated with the detected anomaly;
generating contextual information relating to at least one of the features based on a logical network topology, wherein the logical network topology specifies a plurality of network traffic attributes of the computer network; and
generating an alert that includes a second description of the anomaly and the contextual information relating to the features.
9 . The computer-readable storage medium of claim 8 , wherein the first description of the anomaly is a low-level description of the one or more features and wherein the second description of the anomaly is a human-readable description of the features that includes the contextual information.
10 . The computer-readable storage medium of claim 9 , wherein the operation further comprises:
translating the first description to the second description based on a mapping of at least a first feature of the one or more features to a corresponding component in the computer network.
11 . The computer-readable storage medium of claim 8 , wherein the operation further comprises:
presenting the alert via a user interface.
12 . The computer-readable storage medium of claim 8 , wherein the network traffic attributes include at least one of a connectivity pattern, frequency pattern, and an intensity pattern associated with a component in the computer network.
13 . The computer-readable storage medium of claim 8 , wherein the contextual information describes previously observed network traffic attributes associated with a component in the computer network.
14 . The computer-readable storage medium of claim 8 , wherein the anomaly is generated by a neuro-linguistic behavioral recognition system.
15 . A system, comprising:
a processor; and
a memory storing code, which, when executed on the processor, performs an operation for providing a context-aware description of anomalous behavior in a computer network, comprising:
receiving a first description of an anomaly detected in computer network activity, wherein the first description includes one or more features of the computer network associated with the detected anomaly;
generating contextual information relating to at least one of the features based on a logical network topology, wherein the logical network topology specifies a plurality of network traffic attributes of the computer network; and
generating an alert that includes a second description of the anomaly and the contextual information relating to the features.
16 . The system of claim 15 , wherein the first description of the anomaly is a low-level description of the one or more features and wherein the second description of the anomaly is a human-readable description of the features that includes the contextual information.
17 . The system of claim 16 , wherein the operation further comprises:
translating the first description to the second description based on a mapping of at least a first feature of the one or more features to a corresponding component in the computer network.
18 . The system of claim 15 , wherein the network traffic attributes include at least one of a connectivity pattern, frequency pattern, and an intensity pattern associated with a component in the computer network.
19 . The system of claim 15 , wherein the contextual information describes previously observed network traffic attributes associated with a component in the computer network.
20 . The system of claim 15 , wherein the anomaly is generated by a neuro-linguistic behavioral recognition system.