NETWORK ATTACK VISUALIZATION AND RESPONSE THROUGH INTELLIGENT ICONS

• US 20110066409A1
• Filed: 09/15/2010
• Published: 03/17/2011
• Est. Priority Date: 09/15/2009
• Status: Active Grant

• Current Assignee: Lockheed Martin Corporation (Martin Marietta Corporation)
• Original Assignee: Lockheed Martin Corporation (Martin Marietta Corporation)
• Inventors: Evans, Scott C., Yan, Weizhong, Barnett, Bruce G., Mitchell, Robert J. JR., Scholz, Bernhard J., Markham, T. Stephen, Bejtlich, Richard, Impson, Jeremy, Steinbrecher, Eric
• Granted Patent: US 8,245,302 B2
• Time in Patent Office: Days
• US Class Current: 703/2
• CPC Class Codes: G06F 21/577 Assessing vulnerabilities and evaluating computer system security
• CPC Class Codes: G06F 2221/2101 Auditing as a secondary aspect
• CPC Class Codes: H04L 63/1416 Event detection, e.g. attack signature detection
• CPC Class Codes: H04L 67/75 Indicating network or usage conditions on the user display

Abstract

A network activity visualization system can include an MDL grammar database adapted to store a plurality of MDL grammars, and a pattern matching module adapted to match a received network activity data set against the MDL grammars by calculating a distance of the network activity data set from each MDL grammar. The system can also include an intelligent icon module adapted to receive the MDL grammars and distances of a network data set from each respective MDL grammar, and adapted to generate intelligent icons based on the MDL grammars and distances. The system can further include a display system adapted to display the intelligent icons so as to provide a visual indication of network security.

Claims

1. A network intrusion visualization system comprising:

a computer coupled to a network and adapted to receive data from the network, the computer including a nontransitory computer readable medium having stored thereon software instructions for programming the computer to provide a graphical visualization of monitored network activity, the software instructions, when executed by the computer, cause the computer to perform operations including;

applying a grammar having a plurality of motifs to a network activity data sample to determine a measure of similarity between the data sample and each of a plurality of models representing different network activity behaviors associated with the grammar;

characterizing the data sample based on the measure of similarity, including mapping a normalized difference value for each motif of each grammar to generate a plurality of statistical features;

generating a plurality of intelligent icons, each icon corresponding to one of the models and having a respective plurality of graphical representations each corresponding to a different statistical feature representing the normalized difference value of a respective one of the motifs for that model; and

displaying the intelligent icons and the respective plurality of graphical representations on a display device coupled to the computer.

2. The system of claim 1, wherein the operations further include arranging the graphical representations simultaneously on a display.

3. The system of claim 1, wherein the operations further include arranging the graphical representations based on a relative importance of a corresponding motif within the model associated with that motif.

4. The system of claim 1, wherein the characterizing includes calculating a proximity between the data sample and the models.

5. The system of claim 1, wherein the network activity is classified as normal activity or threat activity based on the characterization of the data sample.

6. The system of claim 1, wherein the network activity is classified as a zero day attack when the data sample is determined to have a distance from each model that is above a predetermined threshold.

7. The system of claim 1, wherein the models include a group of normal network activity models and a group of attack network activity models, both groups being displayed simultaneously.

8. The system of claim 7, wherein the statistical features indicate whether the network activity data is more likely correlated with the group of normal network activity models or with the group of attack network activity models.

9. The system of claim 1, wherein the statistical features indicate the proximity of the network activity relative to one or more of the models.

10. The system of claim 1, wherein the statistical features indicate that the network activity data represents a new network behavior when the statistical features exceed a threshold distance from the models.

11. The system of claim 1, wherein the models are MDL models.

24. The system of claim 1, wherein the network activity data sample is taken from a network connecting a truck and a satellite.

25. The system of claim 1, wherein the operations further include downgrading quality of service, but not terminating, data transfer in the network associated with the network activity data sample based on a measure of similarity between the data sample and one or more of the models associated with an intrusion.

12. A network activity visualization system comprising:

a pattern matching module adapted to match a received network activity data set, containing data representing electronic activity in an electronic communications network, against each of a plurality of mathematical models by calculating a distance of the network activity data set from a respective one of the mathematical models; and

an intelligent icon display module adapted to generate intelligent icons based on the mathematical models and corresponding calculated distances so as to provide a visual indication of network security, the generated intelligent icons adapted for display on a display device.

13. The system of claim 12, wherein when the distance between the network activity data set and each of the mathematical models exceeds a predetermined threshold, the network activity data is identified as a new behavior and a mathematical modeling process is performed on the network activity data to generate a new mathematical model.

14. The system of claim 13, wherein the new model is classified as a normal mathematical model or an attack mathematical model.

15. The system of claim 14, wherein the new model is added to a mathematical model database.

26. The system of claim 12, wherein the network activity data set is taken from a network connecting a truck and a satellite.

27. The system of claim 12, further including downgrading quality of service, but not terminating, data transfer in the network associated with the network activity data set based on a measure of similarity between the data set and one or more of the mathematical models associated with an intrusion.

16. A computer-implemented method of intrusion detection visualization comprising:

characterizing network activity data using a computer programmed to perform network intrusion visualization, the characterizing including generating, with the computer, a plurality of statistical features each representing a relationship between the network activity data and a respective model representing a network activity behavior;

associating, with the computer, each of a plurality of graphical representations with a corresponding one of the models;

altering, with the computer, the visual appearance of each graphical representation based on the statistical feature of the corresponding model to generate altered graphical representations;

downgrading quality of service to a network data transfer associated with the network activity data based on an indication in one of the statistical features that the network activity represents an intrusion; and

displaying one or more of the altered graphical representations on a display device coupled to the computer, the altered graphical representations providing on the display device a visual indication of the corresponding statistical feature.

17. The method of claim 16, further comprising arranging the graphical representations on the display device based on similarity of the statistical features of the graphical representations.

18. The method of claim 16, wherein the characterizing includes calculating, with the computer, a proximity between the compressed network activity data and each model.

19. The method of claim 16, wherein the network activity is classified as normal activity or threat activity based on the characterization.

20. The method of claim 16, wherein the network activity is classified as a zero day attack when the compressed network activity data is determined to have a distance from each of the models that is above a predetermined threshold.

21. The method of claim 16, wherein the models include a group of normal network activity models and a group of attack network activity models.

22. The method of claim 21, wherein the statistical feature indicates whether the network activity data is more likely correlated with the group of normal network activity models or with the group of attack network activity models.

23. The method of claim 16, wherein the models are MDL models.

28. The method of claim 16, wherein the network activity data is received from a network connecting a truck and a satellite.