Method and apparatus for predictive and actual intrusion detection on a network

• US 8,640,234 B2
• Filed: 05/04/2004
• Issued: 01/28/2014
• Est. Priority Date: 05/07/2003
• Status: Active Grant

• Current Assignee: Sysxnet Ltd.
• Original Assignee: Trustwave Holdings Incorporated (Singapore Telecommunications Limited)
• Inventors: Donahue, Thomas P., Gassen, Derek
• Primary Examiner(s): Zand, Kambiz
• Assistant Examiner(s): BAYOU, YONAS A
• Application Number:
  US10/838,863
• Publication Number:
  US 20060150249A1
• Time in Patent Office: 3,556 Days
• Field of Search: 726/23
• US Class Current: 726/23
• CPC Class Codes: G06F 21/554 involving event detection and direct action
• CPC Class Codes: G06F 21/56 Computer malware detection or handling, e.g. anti-virus arrangements
• CPC Class Codes: G06F 21/606 by securing the transmission between two devices or processes
• CPC Class Codes: G06F 21/6209 to a single file or object, e.g. in a secure envelope, encrypted and accessed using a key, or with access control rules appended to the object itself
• CPC Class Codes: H04L 63/1416 Event detection, e.g. attack signature detection
• CPC Class Codes: H04L 63/1441 Countermeasures against malicious traffic countermeasures against attacks on cryptographic mechanisms H04L9/002

Abstract

A method of managing network usage by defining a set of linguistic patterns, where each linguistic pattern is associated with a condition that is to be monitored. Network packets are captured during transmission and analyzed to identify linguistic patterns. Captured network packets are scored based on similarity of at least one linguistic pattern to one or more of the defined set of linguistic patterns. When a packet that is scored above a specified threshold value is identified, at least one responsive action is implemented. In this manner, a system implementing the method is able to identify network traffic that is associated with prospective malicious activity and thereby provide an early warning before damage has occurred.

Claims

1. A method of managing network usage, the method comprising:

defining a set of linguistic patterns, where each linguistic pattern is associated with a condition that is to be monitored;

capturing network packets containing content during transmission;

decapsulating the captured network packets;

identifying linguistic patterns in the content of the captured network packets;

scoring captured network packets based on similarity of at least one of the identified linguistic patterns to one or more of the defined set of linguistic patterns; and

when a packet that is scored above a specified threshold value is identified, implementing at least one responsive action.

2. The method of claim 1 further comprising:

defining a set of categories, wherein each category is associated with a set of linguistic patterns for that category; and

categorizing network packets into one or more of a plurality of categories based upon similarity to one or more of the set of linguistic patterns for that category.

3. The method of claim 1 wherein the capturing comprises passively capturing.

4. The method of claim 1 wherein the capturing comprises actively capturing.

5. The method of claim 1 wherein the decapsulating comprises:

determining from packet header information a type of application layer protocol used by the packet; and

parsing the packet to extract the content from the packet.

6. The method of claim 5 wherein the type of protocol identified in the decapsulating is used to score and categorize the packet.

7. The method of claim 5 wherein the type of protocol identified in the decapsulating is used to provide context for scoring the packet.

8. The method of claim 1 further comprising normalizing information from the decapsulated network packets.

9. The method of claim 1 further comprising parsing the information from the decapsulated network packets.

10. The method of claim 1 further comprising generating a report comprising categorized information of the network packets.

11. A tangible computer readable storage disk or device comprising instructions that, when executed, cause a machine to at least:

define a set of linguistic patterns, where each linguistic pattern is associated with a condition that is to be monitored;

capture network packets containing content during transmission;

decapsulate the captured network packets;

identify linguistic patterns in the content of the captured network packets;

score captured network packets based on similarity of at least one of the identified linguistic patterns to one or more of the defined set of linguistic patterns; and

when a packet that is scored above a specified threshold value is identified, implement at least one responsive action.

12. A monitored networked computing system comprising:

a network;

a plurality of computing devices coupled to the network and configured to exchange information packets containing packet information and content;

a network analyzer coupled to the network, wherein the network analyzer includes mechanisms for capturing the information packets; and

a linguistic analyzer coupled to the network analyzer and operable to identify preselected linguistic patterns in the content of the captured information packets, wherein the linguistic patterns are preselected to identify the information packets that preemptively indicate a future network attack.

13. The monitored network of claim 12 wherein the linguistic analyzer is operable to assign a score based upon a degree to which the linguistic patterns of a particular packet are similar to the preselected linguistic patterns.

14. The monitored network of claim 12 wherein the network analyzer and the linguistic analyzer operate in substantially real time.

15. The monitored network of claim 12 wherein the network analyzer passively captures information packets.

16. The monitored network of claim 12 further comprising means for decapsulating protocol information from the information packet and using the protocol information.

17. The monitored network of claim 12 further comprising a database coupled to the linguistic analyzer for storing the preselected linguistic patterns for each of a plurality of categories.

18. The monitored network of claim 17 wherein the preselected linguistic patterns are represented as regular expressions.

19. The monitored network of claim 12 wherein the network comprises an internet protocol network.

20. The monitored network of claim 12 wherein the network comprises a fibre channel fabric.

21. The monitored network of claim 12 further comprising a report generator coupled to the linguistic analyzer and operable to generate reports based on a categorization of the captured information packets.

22. A device for monitoring network traffic, the device comprising:

a memory comprising instructions; and

a processor to execute the instructions to;

capture network packets containing packet information and content from a network;

identify linguistic patterns in the content of the captured network packets;

score captured network packets based on similarity of at least one of the identified linguistic patterns to one or more of a defined set of linguistic patterns; and

implement at least one responsive action when a packet that is scored above a specified threshold value is identified.

23. A computing device configured to monitor content of network traffic, the computing device comprising:

a processor;

memory coupled to the processor;

a port coupled to an external network; and

computer code executable using the processor and the memory and operable to analyze linguistic patterns in the network traffic content and thereby identify network traffic on the external network by comparing the linguistic patterns in the network traffic to known linguistic patterns.

24. The computing device of claim 23 wherein the computer code is operable to detect network traffic associated with hacker research activity.

25. The computing device of claim 23 wherein the computer code is operable to detect network traffic associated with malicious attack preparation activity.

26. The computing device of claim 23 wherein the computer code is operable to detect network traffic associated with a successfully initiated attack.

27. The computing device of claim 23 wherein the computer code is operable to detect network traffic associated with unauthorized access attempts made to a network resource other than the computing device itself.

28. The computing device of claim 23 wherein the computer code is operable to detect linguistic patterns in the network traffic.

29. The computing device of claim 28 wherein the computer code is operable to score network traffic based on similarity of at least one detected linguistic pattern to one or more preselected linguistic patterns.

30. A method of detecting a prospective network attack, the method comprising:

defining a set of linguistic patterns, where each linguistic pattern is associated with a condition that has been determined to be indicative of a prospective network attack;

monitoring content of network traffic over time;

identifying linguistic patterns when they occur in the network traffic;

accumulating information about the identified occurrences of the defined set of linguistic patterns over time; and

using the accumulated information as a basis for determining, using a processor, a likelihood of a prospective network attack.

31. The method of claim 30 further comprising reporting an occurrence of network traffic when the occurrence of the linguistic patterns in the network traffic exceeds a preselected threshold.

32. The method of claim 30 wherein the accumulating information further comprises maintaining a score based on similarity of at least one identified linguistic pattern to one or more of the defined set of linguistic patterns;

and

when the score exceeds a specified threshold value, implementing at least one responsive action.