Apparatus method and medium for detecting payload anomaly using N-gram distribution of normal data

• US 9,276,950 B2
• Filed: 01/02/2014
• Issued: 03/01/2016
• Est. Priority Date: 11/12/2003
• Status: Active Grant

• Current Assignee: Trustees Of Columbia University In The City Of New York (Columbia University)
• Original Assignee: Trustees Of Columbia University In The City Of New York (Columbia University)
• Inventors: Stolfo, Salvatore J, Wang, Ke
• Primary Examiner(s): PASIA, REDENTOR M
• Application Number:
  US14/146,533
• Publication Number:
  US 20140196147A1
• Time in Patent Office: 789 Days
• Field of Search: 370/392, 370/401, 370/470, 370471-474, 370/476, 726/1, 726/3, 726/11, 726/13, 726/14, 726/22, 726/23, 726/24, 726/25, 713/176, 713/189
• US Class Current: 1/1
• CPC Class Codes: G06F 21/55 Detecting local intrusion or implementing counter-measures
• CPC Class Codes: G06F 21/552 involving long-term monitoring or reporting
• CPC Class Codes: G06F 21/554 involving event detection and direct action
• CPC Class Codes: G06F 21/56 Computer malware detection or handling, e.g. anti-virus arrangements
• CPC Class Codes: G06F 21/562 Static detection
• CPC Class Codes: G06F 21/563 by source code analysis
• CPC Class Codes: G06F 21/564 by virus signature recognition
• CPC Class Codes: H04L 43/00 Arrangements for monitoring or testing data switching networks
• CPC Class Codes: H04L 43/0876 Network utilisation, e.g. volume of load or congestion level
• CPC Class Codes: H04L 63/0218 Distributed architectures, e.g. distributed firewalls
• CPC Class Codes: H04L 63/0245 Filtering by information in the payload
• CPC Class Codes: H04L 63/0263 Rule management
• CPC Class Codes: H04L 63/029 Firewall traversal, e.g. tunnelling or, creating pinholes
• CPC Class Codes: H04L 63/1425 Traffic logging, e.g. anomaly detection
• CPC Class Codes: H04L 63/145 the attack involving the propagation of malware through the network, e.g. viruses, trojans or worms

Abstract

A method, apparatus and medium are provided for detecting anomalous payloads transmitted through a network. The system receives payloads within the network and determines a length for data contained in each payload. A statistical distribution is generated for data contained in each payload received within the network, and compared to a selected model distribution representative of normal payloads transmitted through the network. The model payload can be selected such that it has a predetermined length range that encompasses the length for data contained in the received payload. Anomalous payloads are then identified based on differences detected between the statistical distribution of received payloads and the model distribution. The system can also provide for automatic training and incremental updating of models.

Claims

1. A method for verifying a file type, the method comprising:

receiving, using a hardware processor, a file identified as corresponding to a first file type from a first source;

generating a byte value statistical distribution of the data included in the file received from the first source;

selecting a model byte value statistical distribution representative of the first file type from model byte value statistical distributions representative of a plurality of file types;

determining a distance metric between the byte value statistical distribution of the data included in the file and the selected model byte value statistical distribution; and

verifying that a file type of the received file is the first file type based on a comparison of the distance metric to a distance metric threshold indicating that the file type of received file is the first file type.

2. The method of claim 1, further comprising generating an alert that the file type of the received file is not the first file type based on the comparison of the distance metric to the distance metric threshold indicating that the received file is not of the first file type.

3. The method of claim 1, further comprising inhibiting the file from being executed based on the comparison of the distance metric to the distance metric threshold indicating that the received file is not of the first file type.

4. The method of claim 1, further comprising causing the file to be tested to determine whether the file includes a malicious program based on the comparison of the distance metric to the distance metric threshold indicating that the received file is not of the first file type.

5. The method of claim 1, wherein the byte value statistical distribution of the file is a byte value distribution of the average frequency and variance of data contained in the file, and the selected model distribution is a byte value distribution of the average frequency and variance representative of files of the first file type.

6. The method of claim 1, wherein the byte value statistical distribution of the file is a byte value distribution of the data contained in the file, and the selected model distribution is a byte value distribution of representative of files of the first file type.

7. The method of claim 6, wherein the byte value distribution of the file is a byte frequency count of data contained in the file, and the selected model distribution is a byte frequency count for files of the first file type.

8. The method of claim 6, wherein the byte value distribution of the file is a rank ordered byte frequency count of data contained in the file, and the selected model distribution is a rank ordered byte frequency count for files of the first file type.

9. The method of claim 1, wherein the distance metric is calculated based on a Mahalanobis distance between the byte value statistical distribution of the data included in the file and the selected model byte value statistical distribution.

10. A system for verifying a file type, the system comprising:

a hardware processor that is programmed to;

receive a file identified as corresponding to a first file type from a first source;

generate a byte value statistical distribution of the data included in the file received from the first source;

select a model byte value statistical distribution representative of the first file type from model byte value statistical distributions representative of a plurality of file types;

determine a distance metric between the byte value statistical distribution of the data included in the file and the selected model byte value statistical distribution; and

verify that a file type of the received file is the first file type based on a comparison of the distance metric to a distance metric threshold indicating that the file type of received file is the first file type.

11. The system of claim 10, wherein the hardware processor is further programmed to generate an alert that the file type of the received file is not the first file type based on the comparison of the distance metric to the distance metric threshold indicating that the received file is not of the first file type.

12. The system of claim 10, wherein the hardware processor is further configured to inhibit the file from being executed based on the comparison of the distance metric to the distance metric threshold indicating that the received file is not of the first file type.

13. The system of claim 10, wherein the hardware processor is further configured to cause the file to be tested to determine whether the file includes a malicious program based on the comparison of the distance metric to the distance metric threshold indicating that the received file is not of the first file type.

14. The system of claim 10, wherein the byte value statistical distribution of the file is a byte value distribution of the average frequency and variance of data contained in the file, and the selected model distribution is a byte value distribution of the average frequency and variance representative of files of the first file type.

15. The system of claim 10, wherein the byte value statistical distribution of the file is a byte value distribution of the data contained in the file, and the selected model distribution is a byte value distribution of representative of files of the first file type.

16. The system of claim 15, wherein the byte value distribution of the file is a byte frequency count of data contained in the file, and the selected model distribution is a byte frequency count for files of the first file type.

17. The system of claim 15, wherein the byte value distribution of the file is a rank ordered byte frequency count of data contained in the file, and the selected model distribution is a rank ordered byte frequency count for files of the first file type.

18. The system of claim 10, wherein the distance metric is calculated based on a Mahalanobis distance between the byte value statistical distribution of the data included in the file and the selected model byte value statistical distribution.

19. A non-transitory computer-readable medium containing instructions that, when executed by a processor, cause the processor to perform a method for verifying a file type, the method comprising:

receiving a file identified as corresponding to a first file type from a first source;

generating a byte value statistical distribution of the data included in the file received from the first source;

selecting a model byte value statistical distribution representative of the first file type from model byte value statistical distributions representative of a plurality of file types;

determining a distance metric between the byte value statistical distribution of the data included in the file and the selected model byte value statistical distribution; and

verifying that a file type of the received file is the first file type based on a comparison of the distance metric to a distance metric threshold indicating that the file type of received file is the first file type.