Method and system for detecting algorithm-generated domains

1. A computer-implemented method for detecting algorithm-generated domains (AGDs), the method comprising:

monitoring traffic within an organization's internal network, the internal network communicating with an external network through a border device, a flow preprocessor engine analyzing one or more requested domain names to identify algorithm generated domains corresponding to communications sent by an internal network client within the internal network, wherein the flow preprocessor engine is located inside the internal network;

identifying whether the one or more requested domain names correspond to potential algorithm generated domains;

determining whether the one or more requested domain names that correspond to potential algorithm generated domains exists;

categorizing the one or more requested domain names that exists using one or more curated datasets to generate domain name categorization data;

assigning the one or more requested domain names that exists to one or more bucket data structures;

assigning analysis point data values that correspond to the one or more requested domain names that exists to the one or more bucket data structures based at least in part on domain name categorization data; and

generating reporting data that the one or more requested domain names that exists indicates AGD if the analysis point data values assigned to the one or more bucket data structures exceed a threshold value.

2. The method of claim 1 , further comprising:

categorizing the one or more requested domain names using one or more active services to generate domain name categorization data.

3. The method of claim 1 , further comprising:

determining whether the one or more requested domain names is a potential algorithm generated domain; and

ignoring the one or more requested domain names that is not a potential algorithm generated domain.

4. The method of claim 3 , further comprising:

storing the reporting data for one or more domains requested by the internal network client in a database.

5. The method of claim 1 , further comprising:

specifying the analysis point value for a curated dataset, wherein the specified analysis point value is dynamically modified by a machine-learning scheme; and

analyzing the generated reporting data by the machine-learning scheme to determine whether to adjust the specified analysis point value for the curated dataset based at least on the generated reporting data.

6. The method of claim 5 , further comprising:

generating a certainty score for the one or more domains requested by the internal network client based at least in part on certainty parameters.

7. The method of claim 6 , wherein the certainty parameters are based at least in part on one or more of the following group: necessary conditions, sufficient conditions, time related conditions, or behavior conditions.

8. The method of claim 1 , wherein the one or more curated datasets comprise at least one dataset that corresponds to at least one of the following: evil twin domains, sinkholed domains, sleeper cells, ghost domains, parked domains, or bulk-registered domains.

9. The method of claim 2 , wherein the one or more active services corresponds to at least one of the following: an IP information service, a domain registration service, or a domain popularity service.

10. A system for detecting algorithm-generated domains, comprising:

a computer processor to execute a set of program code instructions;

a memory to hold the program code instructions, in which the program code instructions comprises program code to perform:

monitoring traffic within an organization's internal network, the internal network communicating with an external network through a border device, a flow preprocessor engine analyzing one or more requested domain names to identify algorithm generated domains corresponding to communications sent by an internal network client within the internal network, wherein the flow preprocessor engine is located inside the internal network;

identifying whether the one or more requested domain names correspond to potential algorithm generated domains;

determining whether the one or more requested domain names that correspond to potential algorithm generated domains exists;

categorizing-one or more requested domain names that exists using one or more curated datasets to generate domain name categorization data;

assigning the one or more requested domain names that exists to one or more bucket data structures;

assigning analysis point data values that correspond to the one or more requested domain names that exists to the one or more bucket data structures based at least in part on domain name categorization data; and

generating reporting data that the one or more requested domain names that exists indicates AGD if the analysis point data values assigned to the one or more bucket data structures exceeds a threshold value.

11. The system of claim 10 , in which the program code instructions further comprises program code to categorize the one or more requested domain names using one or more active services to generate domain name categorization data.

12. The system of claim 10 , further comprising:

determining whether the one or more requested domain names is a potential algorithm generated domain; and

ignoring the one or more requested domain names that is not a potential algorithm generated domain.

13. The system of claim 12 , in which the program code instructions further comprises program code to store the reporting data for one or more domains requested by the internal network client in a database.

14. The system of claim 10 , in which the program code instructions further comprises program code to:

specifying the analysis point value for a curated dataset, wherein the specified analysis point value is dynamically modified by a machine-learning scheme; and

analyzing the generated reporting data by the machine-learning scheme to determine whether to adjust the specified analysis point value for the curated dataset based at least on the generated reporting data.

15. The system of claim 14 , in which the program code instructions further comprises program code to generate a certainty score for the one or more domains requested by the internal network client based at least in part on certainty parameters.

16. The system of claim 15 , wherein the certainty parameters are based at least in part on one or more of the following group: necessary conditions, sufficient conditions, time related conditions, or behavior conditions.

17. The system of claim 10 , wherein the one or more curated datasets comprise at least one dataset that corresponds to the following: evil twin domains, sinkholed domains, sleeper cells, ghost domains, parked domains, or bulk-registered domains.

18. The system of claim 11 , wherein one or more the active services corresponds to at least one of the following: an IP information service, a domain registration service, or a domain popularity service.

19. A computer program product embodied on a non-transitory computer readable medium, the non-transitory computer readable medium having stored thereon a sequence of instructions which, when executed by a processor causes the processor to execute a method for detecting algorithm-generated domains (AGDs), the method comprising:

monitoring traffic within an organization's internal network, the internal network communicating with an external network through a border device, a flow preprocessor engine analyzing one or more requested domain names to identify algorithm generated domains corresponding to communications sent by an internal network client within the internal network, wherein the flow preprocessor engine is located inside the internal network;

identifying whether the one or more requested domain names correspond to potential algorithm generated domains;

determining whether the one or more requested domain names that correspond to potential algorithm generated domains exists;

categorizing one or more requested domain names that exists using one or more curated datasets to generate domain name categorization data;

assigning the one or more requested domain names that exists to one or more bucket data structures;

assigning analysis point data values that correspond to the one or more requested domain names that exists to the one or more bucket data structures based at least in part on domain name categorization data; and

generating reporting data that the one or more requested domain names that exists indicates AGD if the analysis point data values assigned to the one or more bucket data structures exceeds a threshold value.

20. The computer program product of claim 19 , wherein the non-transitory computer readable medium further comprises instructions which, when executed by the processor, causes the processor to execute the method further comprising:

categorizing the one or more requested domain names passively using one or more active services to generate domain name categorization data.

21. The computer program product of claim 19 , further comprising:

determining whether the one or more requested domain names is a potential algorithm generated domain; and

ignoring the one or more requested domain names that is not a potential algorithm generated domain.

22. The computer program product of claim 21 , wherein the non-transitory computer readable medium further comprises instructions which, when executed by the processor, causes the processor to execute the method further comprising:

storing the reporting data for one or more domains requested by the internal network client in a database.

23. The computer program product of claim 19 , wherein the non-transitory computer readable medium further comprises instructions which, when executed by the processor, causes the processor to execute the method further comprising:

specifying the analysis point value for a curated dataset, wherein the specified analysis point value is dynamically modified by a machine-learning scheme; and

analyzing the generated reporting data by the machine-learning scheme to determine whether to adjust the specified analysis point value for the curated dataset based at least on the generated reporting data.

24. The computer program product of claim 19 , wherein the non-transitory computer readable medium further comprises instructions which, when executed by the processor, causes the processor to execute the method further comprising:

generating a certainty score for the one or more domains requested by an internal network client based at least in part on certainty parameters.

25. The computer program product of claim 24 , wherein the certainty parameters are based at least in part on one or more of the following group: necessary conditions, sufficient conditions, time related conditions, or behavior conditions.

26. The computer program product of claim 19 , wherein the one or more curated datasets comprise at least one dataset that corresponds to the following: evil twin domains, sinkholed domains, sleeper cells, ghost domains, parked domains, or bulk-registered domains.

27. The computer program product of claim 20 , wherein the one or more active services corresponds to at least one of the following: an IP information service, a domain registration service, or a domain popularity service.