Granted Patent B2

US 9,525,699 · App. 14/041,796 · Granted Dec 20, 2016

Abstract

Claims (17)

1. A method of analysis, comprising:

collecting, using at least one processor circuit in communication with at least one database, NX domain names from at least one asset in at least one real network, the NX domain names being domain names that are not registered;

utilizing, using the at least one processor circuit in communication with at least one database, statistical information about the NX domain names to create testing vectors; and

classifying, using the at least one processor circuit in communication with at least one database, the testing vectors as benign vectors or malicious vectors based on training vectors by comparing the statistical information in the testing vectors to statistical information in training vectors, the statistical information comprising: an average of domain name length; a standard deviation of a domain name length; a number of different top level domains; a length of a domain name excluding a top level domain; a median of a number of unique characters; an average of a number of unique characters; a standard deviation of a number of unique characters; a median of unique 2-grams; an average of unique 2-grams; a standard deviation of unique 2-grams; a frequency of ,com top level domains over frequency of remaining to level domains; a median of unique 3-grams; an average of unique 3-grams; a standard deviation of unique 3-grams; a median count of unique top level domains; an average count of unique top level domains; or a standard deviation count of top level domains; or any combination thereof.

2. The method of claim 1 , further comprising using at least one meta-classifier comprising at least two classifiers.

3. The method of claim 2 , wherein the meta-classifier provides intelligence for identifying new malware.

4. The method of claim 1 , wherein only NX domain traffic is utilized.

5. The method of claim 1 , wherein similar patterns in NX domain names are identified and used to model new botnets.

6. A system of analysis, comprising:

at least one processor circuit in communication with at least one database, the at least one processor circuit connected to at least one network and configured for:

collecting NX domain names from at least one asset in at least one real network, the NX domain names being domain names that are not registered;

utilizing statistical information about the NX domain names to create testing vectors; and

classifying the testing vectors as benign vectors or malicious vectors based on training vectors by comparing the statistical information in the testing vectors to statistical information in training vectors, the statistical information comprising: an average of domain name length; a standard deviation of a domain name length; a number of different top level domains; a length of a domain name excluding a top level domain; a median of a number of unique characters; an average of a number of unique characters; a standard deviation of a number of unique characters; a median of unique 2-grams; an average of unique 2-grams; a standard deviation of unique 2-grams; a frequency of ,com top level domains over frequency of remaining to level domains; a median of unique 3-grams; an average of unique 3-grams; a standard deviation of unique 3-grams; a median count of unique top level domains; an average count of unique top level domains; or a standard deviation count of top level domains; or any combination thereof.

7. The system of claim 6 , further comprising using at least one meta-classifier comprising at least two classifiers.

8. The system of claim 7 , wherein the meta-classifier provides intelligence for identifying new malware.

9. The system of claim 6 , wherein only NX domain traffic is utilized.

10. The system of claim 6 , wherein similar patterns in NX domain names are identified and used to model new botnets.

Assignments (16)