DEVIATION DETECTION OF USAGE PATTERNS OF COMPUTER RESOURCES

• US 20090293121A1
• Filed: 05/21/2008
• Published: 11/26/2009
• Est. Priority Date: 05/21/2008
• Status: Abandoned Application

• Current Assignee: International Business Machines Corporation
• Original Assignee: International Business Machines Corporation
• Inventors: Bigus, Joseph P., Gong, Leon, Lingenfelder, Christoph
• Application Number:
  US12/124,237
• Publication Number:
  US 20090293121A1
• Time in Patent Office: Days
• US Class Current: 726/22
• CPC Class Codes: G06F 21/316 by observing the pattern of computer usage, e.g. typical user behaviour

Abstract

Embodiments of the invention provide a method for detecting changes in behavior of authorized users of computer resources and reporting the detected changes to the relevant individuals. The method includes evaluating actions performed by each user against user behavioral models and business rules. As a result of the analysis, a subset of users may be identified and reported as having unusual or suspicious behavior. In response, the management may provide feedback indicating that the user behavior is due to the normal expected business needs or that the behavior warrants further review. The management feedback is available for use by machine learning algorithms to improve the analysis of user actions over time. Consequently, investigation of user actions regarding computer resources is facilitated and data loss is prevented more efficiently relative to the prior art approaches with only minimal disruption to the ongoing business processes.

Claims

1. A method for monitoring activity of users accessing computer resources, comprising:

collecting a first set of log records documenting user actions in accessing the computer resources during a first time interval;

based on the first set of log records, creating one or more models of user behavior in accessing the computer resources;

collecting a second set of log records documenting user actions in accessing the computer resources during a second time interval;

based on the one or more models of user behavior, analyzing the second set of log records to identify, for each user, changes in behavior exhibited during the second time interval, relative to the behavior of each respective user exhibited during the first time interval;

based on the identified changes in behavior, identifying a predefined suspicious activity engaged in by at least one user in accessing the computer resources during the second time interval; and

generating an alert message identifying the suspicious activity engaged in by the at least one user in accessing the computer resources.

2. The method of claim 1, wherein the step of creating one or more models of user behavior comprises:

aggregating the first set of log records at one or more levels according to a type of data included in the first set of log records and processing requirements;

selecting one or more model types, wherein each model type is used to evaluate the first set of log records;

selecting one or more attributes from the first set of log records;

aggregating data associated with the one or more selected attributes into one or more mining tables according to the one or more levels;

selecting algorithm parameters for the selected one or more model types; and

creating the one or more models of user behavior by running the selected one or more model types using the aggregated data in the one or more mining tables and the selected algorithm parameters.

3. The method of claim 2, further comprising, validating the one or more models of user behavior according to a test procedure.

4. The method of claim 3, wherein the test procedure comprises performing statistical analysis of predictive and generalization capabilities of the one or more models of user behavior.

5. The method of claim 2, wherein the one or more model types comprise a distribution-based clustering model, a center-based clustering model, and/or an association rule model.

6. The method of claim 5, wherein the one or more models of user behavior comprise one or more clusters labeled according to perceived user roles.

7. The method of claim 2, wherein the algorithm parameters comprise learning rate, numbers of clusters, and/or similarity measures.

8. The method of claim 1, wherein the step of analyzing the second set of log records comprises performing quantitative clustering based on activity frequency and association rules.

9. The method of claim 1, further comprising, updating the one or more models of user behavior based on a feedback received from a recipient of the alert message regarding the suspicious activity engaged in by the at least one user.

10. The method of claim 1, wherein the computer resources comprise computer source code.

11. A computer-readable storage medium storing a computer program which, when executed by a processor, performs operations, the operations comprising:

collecting a first set of log records documenting user actions in accessing the computer resources during a first time interval;

based on the first set of log records, creating one or more models of user behavior in accessing the computer resources;

collecting a second set of log records documenting user actions in accessing the computer resources during a second time interval;

based on the identified changes in behavior, identifying a predefined suspicious activity engaged in by at least one user in accessing the computer resources during the second time interval;

based on the identified changes in behavior, identifying a suspicious activity engaged in by at least one user in accessing the computer resources during the second time interval; and

generating an alert message identifying the suspicious activity engaged in by the at least one user in accessing the computer resources.

12. The computer-readable storage medium of claim 11, wherein creating the one or more models of user behavior comprises:

aggregating the first set of log records at one or more levels according to a type of data included in the first set of log records and processing requirements;

selecting one or more model types, wherein each model type is used to evaluate the first set of log records;

selecting one or more attributes from the first set of log records;

aggregating data associated with the one or more selected attributes into one or more mining tables according to the one or more levels;

specifying values of algorithm parameters for the selected one or more model types; and

creating the one or more models of user behavior by running the selected one or more model types using the aggregated data in the one or more mining tables and the selected algorithm parameters.

13. The computer-readable storage medium of claim 12, wherein the one or more model types comprise a distribution-based clustering model, a center-based clustering model, and/or an association rule model.

14. The computer-readable storage medium of claim 13, wherein the one or more models of user behavior comprise one or more clusters labeled according to perceived user roles.

15. The computer-readable storage medium of claim 11, wherein analyzing the second set of log records comprises performing quantitative clustering based on activity frequency and association rules.

16. The computer-readable storage medium of claim 11, further comprising updating the one or more models of user behavior based on a feedback received from a recipient of the alert message regarding the suspicious activity engaged in by the at least one user.

17. The computer-readable storage medium of claim 11, wherein the computer resources comprise computer source code.

18. A system, comprising:

a processor; and

a memory containing a program, which when executed by the processor is configured to monitor the activity of users in accessing computer resources by performing the steps of;

collecting a first set of log records documenting user actions in accessing the computer resources during a first time interval,

based on the first set of log records, creating one or more models of user behavior in accessing the computer resources,

collecting a second set of log records documenting user actions in accessing the computer resources during a second time interval,

based on the one or more models of user behavior, analyzing the second set of log records to identify, for each user, changes in behavior exhibited during the second time interval, relative to the behavior of each respective user exhibited during the first time interval,

based on the identified changes in behavior, identifying a predefined suspicious activity engaged in by at least one user in accessing the computer resources during the second time interval, and

documenting the suspicious activity engaged in by the at least one user in accessing the computer resources.

19. The system of claim 18, wherein the step of creating the one or more models of user behavior comprises:

aggregating the first set of log records at one or more levels according to a type of data included in the first set of log records and processing requirements;

selecting one or more model types, wherein each model type is used to evaluate the first set of log records;

selecting one or more attributes from the first set of log records;

aggregating data associated with the one or more selected attributes into one or more mining tables according to the one or more levels;

specifying values of algorithm parameters for the selected one or more model types; and

creating the one or more models of user behavior by running the selected one or more model types using the aggregated data in the one or more mining tables and the selected algorithm parameters.

20. The system of claim 19, wherein the one or more model types comprise a distribution-based clustering model, a center-based clustering model, and/or an association rule model.

21. The system of claim 20, wherein the one or more models of user behavior comprise one or more clusters labeled according to perceived user roles.

22. The system of claim 18, wherein the step of analyzing the second set of log records comprises performing quantitative clustering based on activity frequency and association rules.

23. The system of claim 18, further comprising updating the one or more models of user behavior based on a feedback received from a recipient of the alert message regarding the suspicious activity engaged in by the at least one user.

24. The system of claim 18, wherein the computer resources comprise computer source code.