Automatic classification mechanism of malicious code based on A_Kohonen algorithm

Xinheng Wang

Research output: Contribution to journalArticle

Abstract

The current mass of malicious code reports has become a huge burden of cloud-security-based anti-virus network systems.The utilization of efficient,scientific and automatic classification mechanism is the basic premise for responding quickly to large-scale known and unknown malicious codes and their new variants.In order to achieve the automatic classification of malicious codes,we improved the Kohonen algorithm,a classic neural network model with no mentors and proposed a new neural network model A_Kohonen with part supervised learning of the process.Then the A_Kohonen-based automatic classification mechanism of malicious codes was provided to support anti-virus experts to refine and analyze malicious codes further.Experimental analysis shows that the mechanism can initially classify malicious codes effectively and accurately.
Translated title of the contributionAutomatic classification mechanism of malicious code based on A_Kohonen algorithm
Original languageChinese
Pages (from-to)178-182
Number of pages5
JournalComputer Science
Volume41
Issue number8
DOIs
Publication statusPublished - 16 Dec 2013

Fingerprint

Viruses
Neural networks
Supervised learning
Neural Network Model
Virus
Supervised Learning
Classify
Unknown

Cite this

Wang, Xinheng. / 一种基于A_Kohonen算法的恶意代码自动分类机制. In: Computer Science. 2013 ; Vol. 41, No. 8. pp. 178-182.
@article{0f4b16fff69f4dcaab4fcb7f884d2ede,
title = "一种基于A_Kohonen算法的恶意代码自动分类机制",
abstract = "The current mass of malicious code reports has become a huge burden of cloud-security-based anti-virus network systems.The utilization of efficient,scientific and automatic classification mechanism is the basic premise for responding quickly to large-scale known and unknown malicious codes and their new variants.In order to achieve the automatic classification of malicious codes,we improved the Kohonen algorithm,a classic neural network model with no mentors and proposed a new neural network model A_Kohonen with part supervised learning of the process.Then the A_Kohonen-based automatic classification mechanism of malicious codes was provided to support anti-virus experts to refine and analyze malicious codes further.Experimental analysis shows that the mechanism can initially classify malicious codes effectively and accurately.",
author = "Xinheng Wang",
year = "2013",
month = "12",
day = "16",
doi = "10.11896/j.issn.1002-137X.2014.08.039",
language = "Chinese",
volume = "41",
pages = "178--182",
journal = "Computer Science",
issn = "1508-2806",
publisher = "AGH University of Science and Technology",
number = "8",

}

一种基于A_Kohonen算法的恶意代码自动分类机制. / Wang, Xinheng.

In: Computer Science, Vol. 41, No. 8, 16.12.2013, p. 178-182.

Research output: Contribution to journalArticle

TY - JOUR

T1 - 一种基于A_Kohonen算法的恶意代码自动分类机制

AU - Wang, Xinheng

PY - 2013/12/16

Y1 - 2013/12/16

N2 - The current mass of malicious code reports has become a huge burden of cloud-security-based anti-virus network systems.The utilization of efficient,scientific and automatic classification mechanism is the basic premise for responding quickly to large-scale known and unknown malicious codes and their new variants.In order to achieve the automatic classification of malicious codes,we improved the Kohonen algorithm,a classic neural network model with no mentors and proposed a new neural network model A_Kohonen with part supervised learning of the process.Then the A_Kohonen-based automatic classification mechanism of malicious codes was provided to support anti-virus experts to refine and analyze malicious codes further.Experimental analysis shows that the mechanism can initially classify malicious codes effectively and accurately.

AB - The current mass of malicious code reports has become a huge burden of cloud-security-based anti-virus network systems.The utilization of efficient,scientific and automatic classification mechanism is the basic premise for responding quickly to large-scale known and unknown malicious codes and their new variants.In order to achieve the automatic classification of malicious codes,we improved the Kohonen algorithm,a classic neural network model with no mentors and proposed a new neural network model A_Kohonen with part supervised learning of the process.Then the A_Kohonen-based automatic classification mechanism of malicious codes was provided to support anti-virus experts to refine and analyze malicious codes further.Experimental analysis shows that the mechanism can initially classify malicious codes effectively and accurately.

U2 - 10.11896/j.issn.1002-137X.2014.08.039

DO - 10.11896/j.issn.1002-137X.2014.08.039

M3 - Article

VL - 41

SP - 178

EP - 182

JO - Computer Science

JF - Computer Science

SN - 1508-2806

IS - 8

ER -