Method and system for detecting malware

• US 9,525,699 B2
• Filed: 09/30/2013
• Issued: 12/20/2016
• Est. Priority Date: 01/06/2010
• Status: Active Grant

• Current Assignee: Ecrime Management Strategies, Inc.
• Original Assignee: Damballa Incorporated
• Inventors: Perdisci, Robert, Antonakakis, Emmanouil, Lee, Wenke, Ollmann, Gunter
• Primary Examiner(s): THIAW, CATHERINE B
• Application Number:
  US14/041,796
• Publication Number:
  US 20140101759A1
• Time in Patent Office: 1,177 Days
• US Class Current: 1/1
• CPC Class Codes: G06F 21/577 Assessing vulnerabilities and evaluating computer system security
• CPC Class Codes: G06F 9/45508 Runtime interpretation or emulation, e g. emulator loops, bytecode interpretation
• CPC Class Codes: G06N 20/00 Machine learning
• CPC Class Codes: H04L 61/4511 using domain name system [DNS]
• CPC Class Codes: H04L 63/14 for detecting or protecting against malicious traffic
• CPC Class Codes: H04L 63/1408 by monitoring network traffic monitoring network traffic per se H04L43/00
• CPC Class Codes: H04L 63/1416 Event detection, e.g. attack signature detection
• CPC Class Codes: H04L 63/145 the attack involving the propagation of malware through the network, e.g. viruses, trojans or worms
• CPC Class Codes: H04L 63/1491 using deception as countermeasure, e.g. honeypots, honeynets, decoys or entrapment
• CPC Class Codes: H04L 9/40 Network security protocols

Abstract

A system and method of analysis. NX domain names are collected from an asset in a real network. The NX domain names are domain names that are not registered. The real network NX domain names are utilized to create testing vectors. The testing vectors are classified as benign vectors or malicious vectors based on training vectors. The asset is then classified as infected if the NX testing vector created from the real network NX domain names is classified as a malicious vector.

Claims

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.