TRAFFIC FEATURE INFORMATION EXTRACTION DEVICE, TRAFFIC FEATURE INFORMATION EXTRACTION METHOD, AND TRAFFIC FEATURE INFORMATION EXTRACTION PROGRAM

Abstract

A traffic characteristic information extracting device includes a memory, and processing circuitry coupled to the memory and configured to acquire traffic information satisfying a predetermined condition from network traffic data, extract characteristic information from the acquired traffic information, classify the traffic information based on the extracted characteristic information, analyze a classification result obtained at the classifying and generate signatures, and output a signature satisfying a predetermined condition among the generated signatures.

Description

TECHNICAL FIELD

The present invention relates to a traffic characteristic information extracting device, a traffic characteristic information extracting method, and a traffic characteristic information extracting program.

BACKGROUND ART

In recent years, according to the spread of the Internet, cyberattacks conducted using malicious software called malware have been increasing. There has been a method of, in detecting a terminal infected with the malware, extracting characteristic information based on header information of traffic transmitted by the terminal, generating a signature, and performing matching with a blacklist.

CITATION LIST

Patent Literature

[PTL 1] Japanese Patent No. 6053091

SUMMARY OF THE INVENTION

Technical Problem

However, in the conventional technique described above, there have been problems described below. For example, since an attacker changes setting of a server acting as a playmaker in order to avoid detection, even if infection is confirmed by the matching, in some case, a communication destination server is absent or is a normal server. Even if the terminal communicates with a server of the attacker, an attack does not always succeed. Accordingly, even if the signature matches, it cannot be surely determined that the terminal is truly infected with the malware and is receiving damage (for example, operation by the attacker).

A disclosed technique is devised in view of the above, and an object of the disclosed technique is to provide a traffic characteristic information extracting device, a traffic characteristic information extracting method, and a traffic characteristic information extracting program that can accurately determine whether a terminal is receiving damage.

Means for Solving the Problem

In order to solve the problems and achieve the object, in an aspect, a traffic characteristic information extracting device disclosed by this application includes: an acquiring unit that acquires traffic information satisfying a predetermined condition from network traffic data; an extracting unit that extracts characteristic information from the acquired traffic information; a classifying unit that classifies the traffic information based on the extracted characteristic information; a generating unit that analyzes a classification result obtained by the classifying unit and generates signatures; and an output unit that outputs a signature satisfying a predetermined condition among the generated signatures.

In an aspect, a traffic characteristic information extracting method disclosed by this application includes: an acquiring step in which a traffic characteristic information extracting device acquires traffic information satisfying a predetermined condition from network traffic data; an extracting step in which the traffic characteristic information extracting device extracts characteristic information from the acquired traffic information; a classifying step in which the traffic characteristic information extracting device classifies the traffic information based on the extracted characteristic information; a generating step in which the traffic characteristic information extracting device analyzes a classification result obtained in the classifying step and generates signatures; and an output step in which the traffic characteristic information extracting device outputs a signature satisfying a predetermined condition among the generated signatures.

Further, in an aspect, a traffic characteristic information extracting program disclosed by this application causes a computer to execute: an acquiring step of acquiring traffic information satisfying a predetermined condition from network traffic data; an extracting step of extracting characteristic information from the acquired traffic information; a classifying step of classifying the traffic information based on the extracted characteristic information; a generating step of analyzing a classification result obtained in the classifying step and generating signatures; and an output step of outputting a signature satisfying a predetermined condition among the generated signatures.

Effects of the Invention

The traffic characteristic information extracting device, the traffic characteristic information extracting method, and the traffic characteristic information extracting program disclosed by this application exert an effect that it is possible to accurately determine whether a terminal is receiving damage.

BRIEF DESCRIPTION OF DRAWINGS

FIG. 1 is a diagram illustrating the configuration of a reception traffic characteristic extraction server.

FIG. 2 is a flowchart for explaining the operation of the reception traffic characteristic extraction server.

FIG. 3 is a diagram illustrating that information processing by a traffic characteristic information extracting program is specifically realized using a computer.

DESCRIPTION OF EMBODIMENTS

An embodiment of a traffic characteristic information extracting device, a traffic characteristic information extracting method, and a traffic characteristic information extracting program disclosed by this application is explained in detail below with reference to the drawings. Note that the traffic characteristic information extracting device, the traffic characteristic information extracting method, and the traffic characteristic information extracting program disclosed by this application are not limited by the embodiment explained below.

First, the configuration of the traffic characteristic information extracting device according to an embodiment disclosed by this application is explained. FIG. 1 is a diagram illustrating the configuration of a reception traffic characteristic extraction server 10. As illustrated in FIG. 1, the reception traffic characteristic extraction server 10 includes an input unit 11, a characteristic-information extracting unit 12, a clustering unit 13, a signature generating unit 14, and an output unit 15. These constituent portions are connected such that input and output of signals and data are possible in one direction or both directions.

The input unit 11 acquires traffic information satisfying a predetermined condition from network traffic data 11a. The characteristic-information extracting unit 12 extracts characteristic information from the acquired traffic information. The clustering unit 13 classifies the traffic information based on the extracted characteristic information. The signature generating unit 14 analyzes a classification result obtained by the clustering unit 13 and generates signatures. The output unit 15 outputs a signature satisfying (matching) a predetermined condition among the generated signatures.

Next, the operation of the reception traffic characteristic extraction server 10 according to the embodiment disclosed by this application is explained. FIG. 2 is a flowchart for explaining the operation of the reception traffic characteristic extraction server 10.

First, in S1, the reception traffic characteristic extraction server 10 acquires, with the input unit 11, traffic information satisfying a predetermined condition from the network traffic data 11a. In next S2, the reception traffic characteristic extraction server 10 extracts, with the characteristic-information extracting unit 12, characteristic information from the acquired traffic information. In S3, the reception traffic characteristic extraction server 10 classifies, with the clustering unit 13, the traffic information based on the extracted characteristic information. In S4, the reception traffic characteristic extraction server 10 analyzes, with the signature generating unit 14, a classification result obtained by the clustering unit 13 and generates signatures. In S5, the reception traffic characteristic extraction server 10 outputs, with the output unit 15, a signature satisfying a predetermined condition among the generated signatures.

In the reception traffic characteristic extraction server 10, the characteristic-information extracting unit 12 may extract the characteristic information based on at least one of information included in a header portion, information included in a transmission data portion, and information included in a reception data portion of the network traffic data. The clustering unit 13 may classify the traffic information using unsupervised machine learning in which learning data serving as teacher information is not used. Consequently, it is possible to determine, based on a more highly accurate classification result, whether the terminal is receiving damage. Further, in analyzing the classification result, the signature generating unit 14 may generate the signatures through a frequently appearing pattern analysis or a frequently appearing character string analysis.

The frequently appearing pattern analysis may be an analysis of the information included in the header portion of the network traffic data and, more suitably, may be an analysis performed using frequently appearing pattern mining. Consequently, it is possible to determine, based on a more highly accurate analysis result, whether the terminal is receiving damage. Alternatively, the frequently appearing pattern analysis may be an analysis of the information included in the transmission data portion and the information included in the reception data portion of the network traffic data. Further, the traffic information may be traffic information of reception traffic that the terminal receives when the terminal communicates with a specific server (for example, a malicious server).

In other words, the reception traffic characteristic extraction server 10 analyzes the network traffic data 11a to thereby convert traffic received by the terminal into a signature and detects that communication with a communication destination server (for example, a malicious server) is performed. Simply by detecting the traffic transmitted by the terminal, it is sometimes unknown whether the communication destination server is malicious. However, the reception traffic characteristic extraction server 10 also extracts characteristics of the traffic received by the terminal and converts a response from the communication destination server into a signature. Therefore, it is possible to surely determine that the terminal is infected with malware or an attack is successful. That is, by examining the response from the communication destination server, it is possible to accurately determine whether the terminal is receiving damage. In the determination, more information such as information concerning a payload not used in the past is extracted as characteristics. Therefore, it is also possible to achieve improvement of a detection ratio and a reduction of a misdetection ratio.

As an application example of the reception traffic characteristic extraction server 10, when network traffic of a malware-infected terminal is given as input traffic data, whereby the terminal is infected with malware, the reception traffic characteristic extraction server 10 can extract characteristics of traffic received from a malicious server and convert the characteristics into a signature. Therefore, the reception traffic characteristic extraction server 10 can determine based on presence or absence of an output of a signature satisfying the predetermined condition that the terminal is infected with malware or the attack is successful. For example, when an output of a signature satisfying the predetermined condition is present, the reception traffic characteristic extraction server 10 can surely conclude that the terminal is infected with malware or the attack is successful.

As another application example, by reproducing malicious traffic and discriminating a response from a server used by the attacker and responses from other servers, the reception traffic characteristic extraction server 10 can find the server used by the attacker.

(Traffic Characteristic Information Extracting Program)

FIG. 3 is a diagram illustrating that information processing by a traffic characteristic information extracting program is specifically realized using a computer 100. As illustrated in FIG. 3, the computer 100 includes, for example, a memory 101, a CPU (Central Processing Unit) 102, a hard disk drive interface 103, a disk drive interface 104, a serial port interface 105, a video adapter 106, and a network interface 107. These units are connected by a bus C.

The memory 101 includes, as illustrated in FIG. 3, a ROM (Read Only Memory) 101a and a RAM (Random Access Memory) 101b. The ROM 101a stores a boot program such as a BIOS (Basic Input Output System). The hard disk drive interface 103 is connected to a hard disk drive 108 as illustrated in FIG. 3. The disk drive interface 104 is connected to a disk drive 109 as illustrated in FIG. 3. A detachable storage medium such as a magnetic disk or an optical disk is inserted into the disk drive 109. The serial port interface 105 is connected to, for example, a mouse 110 and a keyboard 111 as illustrated in FIG. 3. The video adapter 106 is connected to, for example, a display 112 as illustrated in FIG. 3.

As illustrated in FIG. 3, the hard disk drive 108 stores, for example, an OS (Operating System) 108a, an application program 108b, a program module 108c, program data 108d, network traffic data, traffic information, characteristic information, and a signature. That is, the traffic characteristic information extracting program according to the disclosed technique is stored in, for example, the hard disk drive 108 as the program module 108c in which a command to be executed by the computer 100 is described. Specifically, the program module 108c in which various procedures for executing the same information processing as the information processing of each of the input unit 11, the characteristic-information extracting unit 12, the clustering unit 13, the signature generating unit 14, and the output unit 15, which are described in the above embodiment, is stored in the hard disk drive 108. Data to be used for the information processing by the traffic characteristic information extracting program is stored in, for example, the hard disk drive 108 as the program data 108d. The CPU 102 reads out the program module 108c and the program data 108d stored in the hard disk drive 108 to the RAM 101b according to necessity and executes the various procedures.

Note that the program module 108c and the program data 108d relating to the traffic characteristic information extracting program is not limited to the storage in the hard disk drive 108 and may be stored in, for example, a detachable storage medium and read out by the CPU 102 via the disk drive 109 or the like. Alternatively, the program module 108c and the program data 108d relating to the traffic characteristic information extracting program may be stored in another computer connected via a network (a LAN (Local Area Network), a WAN (Wide Area Network), or the like) and read out by the CPU 102 via the network interface 107.

The components of the reception traffic characteristic extraction server 10 explained above are not always required to be physically configured as illustrated. That is, a specific form of distribution and integration of the devices is not limited to the illustrated form. All or a part of the devices can also be configured to be mechanically or physically distributed and integrated in any units according to various loads, states of use, and the like. For example, the clustering unit 13 and the signature generating unit 14 or a frequently-appearing-pattern analyzing unit 141 and a frequently-appearing-character-string analyzing unit 142 may be integrated as one component. Conversely, the signature generating unit 14 may be distributed to a portion that performs the frequently appearing pattern analysis and a portion that performs the frequently appearing character string analysis. Further, the hard disk drive 108 that stores the network traffic data, the traffic information, the characteristic information, and the signature may be connected through a network or a cable as an external device of the reception traffic characteristic extraction server 10.

REFERENCE SIGNS LIST

• 10 Reception traffic characteristic extraction server
• 11 Input unit
• 11 a Network traffic data
• 12 Characteristic-information extracting unit
• 13 Clustering unit
• 14 Signature generating unit
• 15 Output unit
• 15 a Signature
• 100 Computer
• 101 Memory
• 101 a ROM
• 101 b RAM
• 102 CPU
• 103 Hard disk drive interface
• 104 Disk drive interface
• 105 Serial port interface
• 106 Video adapter
• 107 Network interface
• 108 Hard disk drive
• 108 a OS
• 108 b Application program
• 108 c Program module
• 108 d Program data
• 109 Disk drive
• 110 Mouse
• 111 Keyboard
• 112 Display
• 141 Frequently-appearing-pattern analyzing unit
• 142 Frequently-appearing-character-string analyzing unit

Claims

1. A traffic characteristic information extracting device comprising: a memory; andprocessing circuitry coupled to the memory and configured to:acquire traffic information satisfying a predetermined condition from network traffic dataextract characteristic information from the acquired traffic informationclassify the traffic information based on the extracted characteristic informationanalyze a classification result obtained at the classifying and generate signatures andoutput a signature satisfying a predetermined condition among the generated signatures.

2. The traffic characteristic information extracting device according to claim 1, wherein the processing circuitry is further configured to extract the characteristic information based on at least one of information included in a header portion, information included in transmitted data, and information included in received data of the network traffic data.

3. The traffic characteristic information extracting device according to claim 1, wherein the processing circuitry is further configured to classify the traffic information using machine learning.

4. The traffic characteristic information extracting device according to claim 1, wherein, in analyzing the classification result, the processing circuitry is further configured to generate the signatures through a frequently appearing pattern analysis or a frequently appearing character string analysis.

5. The traffic characteristic information extracting device according to claim 4, wherein the frequently appearing pattern analysis is an analysis of information included in a header portion of the network traffic data.

6. The traffic characteristic information extracting device according to claim 4, wherein the frequently appearing pattern analysis is an analysis of information included in transmitted data and information included in received data of the network traffic data.

7. A traffic characteristic information extracting method that is performed by a traffic characteristic information extracting device, the traffic characteristic information extracting method comprising: acquiring traffic information satisfying a predetermined condition from network traffic data;extracting characteristic information from the acquired traffic information;classifying the traffic information based on the extracted characteristic information;analyzing a classification result obtained at the classifying and generating signatures; andoutputting a signature satisfying a predetermined condition among the generated signatures.

8. A non-transitory computer-readable recording medium storing therein a traffic characteristic information extracting program that causes a computer to execute a process comprising: acquiring traffic information satisfying a predetermined condition from network traffic data;extracting characteristic information from the acquired traffic information;classifying the traffic information based on the extracted characteristic information;analyzing a classification result obtained at the classifying and generating signatures; andoutputting a signature satisfying a predetermined condition among the generated signatures.