Detection of malware beaconing activities

Patent metadata

Field	Value
Publication number	US-9038178-B1
Application number	US-201213532385-A
Country	US
Kind code	B1
Filing date	Jun 25, 2012
Priority date	Jun 25, 2012
Publication date	May 19, 2015
Grant date	May 19, 2015

Abstract

Malware beaconing activity detection is disclosed, including: monitoring a plurality of conversations between an internal device and one or more external destinations; extracting feature sets based at least in part on the plurality of conversations; and determining that a conversation of the plurality of conversations is anomalous based at least in part on the extracted feature sets.

First claim

What is claimed is:

1. A malware beaconing detection system, comprising:
a processor configured to:
identify a plurality of conversations between an internal device and one or more external destinations, wherein at least some of the plurality of conversations are determined from stored logs associated with communication between one or more internal devices associated with an enterprise network and the one or more external destinations, wherein identifying a first conversation of the plurality of conversations between a pair comprising the internal device and a first external destination of the one or more external destination comprises to:
obtain a plurality of communication events among the stored logs that includes the pair comprising the internal device and the first external destination, wherein to obtain a communication event that includes the pair comprising the internal device and the first external destination includes to:
identify traffic between a dynamically assigned Internal Protocol (IP) address and the first external destination; and
determine that the dynamically assigned IP address maps to a statically assigned address associated with the internal device; and

generate the first conversation between the pair comprising the internal device and the first external destination based at least in part on the plurality of communication events;

extract feature sets based at least in part on the plurality of conversations; and
determine that a conversation of the plurality of conversations is anomalous based at least in part on the extracted feature sets; and

a memory coupled to the processor and configured to store the extracted feature sets.

2. The system of claim 1 , wherein at least one of the one or more external destinations comprises an external IP address outside of the enterprise network.

3. The system of claim 1 , wherein the at least some of the plurality of conversations are determined based at least in part on stored logs comprising one or more of the following: firewall logs, proxy logs, and dynamic host configuration protocol (DHCP) logs.

4. The system of claim 1 , wherein the anomalous conversation is potentially indicative of malware being present at the internal device.

5. The system of claim 1 , wherein to determine that the conversation is anomalous includes building a model based at least in part on at least some of the feature sets and a plurality of historical conversations.

6. The system of claim 5 , wherein at least some of the extracted feature sets are input into the model and the model is configured to determine that the conversation is anomalous based on the inputted feature sets.

7. The system of claim 1 , wherein one of the feature sets includes a feature associated with an age of the internal device.

8. The system of claim 1 , wherein one of the feature sets includes a feature associated with an age of one of the one or more external destinations.

9. The system of claim 1 , wherein one of the feature sets includes a feature associated with a service associated with one of the one or more external destinations.

10. The system of claim 1 , wherein one of the feature sets includes a feature associated with a geolocation of one of the one or more external destinations.

11. The system of claim 1 , wherein the processor is further configured to present information associated the anomalous conversation.

12. The system of claim 1 , wherein identifying the first conversation further includes the processor being further configured to store attributes associated with the plurality of communication events, the internal device, and the first external destination with the first conversation, and wherein extracting feature sets includes the processor being further configured to extract a feature set from the attributes associated with the first conversation.

13. A method for malware beaconing detection, comprising:
identifying a plurality of conversations between an internal device and one or more external destinations, wherein at least some of the plurality of conversations are determined from stored logs associated with communication between one or more internal devices associated with an enterprise network and the one or more external destinations, wherein identifying a first conversation of the plurality of conversations between a pair comprising the internal device and a first external destination of the one or more external destination comprises:
obtaining a plurality of communication events among the stored logs that includes the pair comprising the internal device and the first external destination, wherein to obtain a communication event that includes the pair comprising the internal device and the first external destination includes:
identifying traffic between a dynamically assigned Internal Protocol (IP) address and the first external destination; and
determining that the dynamically assigned IP address maps to a statically assigned address associated with the internal device; and

generating the first conversation between the pair comprising the internal device and the first external destination based at least in part on the plurality of communication events;

extracting feature sets based at least in part on the plurality of conversations; and
determining, using a processor, that a conversation of the plurality of conversations is anomalous based at least in part on the extracted feature sets.

14. The method of claim 13 , wherein at least some of the plurality of conversations are determined based at least in part on stored logs comprising one or more of the following: firewall logs, proxy logs, and dynamic host configuration protocol (DHCP) logs.

15. The method of claim 13 , wherein determining that the conversation is anomalous includes building a model based at least in part on at least some of the feature sets and a plurality of historical conversations.

16. The method of claim 15 , wherein at least some of the extracted feature sets are input into the model and the model is configured to determine that the conversation is anomalous based on the inputted feature sets.

17. The method of claim 13 , further comprising presenting information associated the anomalous conversation.

18. A computer program product for malware beaconing detection, the computer program product being embodied in a non-transitory computer readable storage medium and comprising computer instructions for:
identifying a plurality of conversations between an internal device and one or more external destinations, wherein at least some of the plurality of conversations are determined from stored logs associated with communication between one or more internal devices associated with an enterprise network and the one or more external destinations, wherein identifying a first conversation of the plurality of conversations between a pair comprising the internal device and a first external destination of the one or more external destination comprises:
obtaining a plurality of communication events among the stored logs that includes the pair comprising the internal device and the first external destination, wherein to obtain a communication event that includes the pair comprising the internal device and the first external destination includes:
identifying traffic between a dynamically assigned Internal Protocol (IP) address and the first external destination; and
determining that the dynamically assigned IP address maps to a statically assigned address associated with the internal device; and

generating the first conversation between the pai

Assignees

• Lin Derek
• Emc Corp

Inventors

• Lin Derek

Classifications

• H04L63/02

  for separating internal from external traffic, e.g. firewalls · CPC title

• H04L63/1416 Primary

  Event detection, e.g. attack signature detection · CPC title

• H04L63/1441

  Countermeasures against malicious traffic (countermeasures against attacks on cryptographic mechanisms H04L9/002) · CPC title

• H04L63/1425 Primary

  Traffic logging, e.g. anomaly detection · CPC title