计算机工程与应用 ›› 2011, Vol. 47 ›› Issue (7): 125-127.

• 网络、通信、安全 • 上一篇    下一篇

基于Win32 API和SVM的未知病毒检测方法

王晓燕,金 聪,谈华永   

  1. 华中师范大学 计算机科学系,武汉 430079
  • 收稿日期:1900-01-01 修回日期:1900-01-01 出版日期:2011-03-01 发布日期:2011-03-01

Unknown virus detection method based on Win32 API and SVM

WANG Xiaoyan,JIN Cong,TAN Huayong   

  1. Department of Computer Science,China Central Normal University,Wuhan 430079,China
  • Received:1900-01-01 Revised:1900-01-01 Online:2011-03-01 Published:2011-03-01

摘要: 提出了一种Windows平台下检测未知病毒的新方法,该方法通过分析PE文件调用的Win32 API序列,用SVM来对划分后k长度的API短序列分类,并通过分析API函数及参数危险程度来提高SVM分类的精确度,从而实现对未知病毒的检测。实验结果表明,该方法实现的病毒检测系统比只用SVM的系统具有更好的检测效果。

关键词: 未知病毒, Win32 API序列, 支持向量机

Abstract: This paper proposes a new approach to detect the unknown viruses under the Windows platform.The main aim of the method is to achieve the detection of unknown viruses by analyzing the Win32API sequences of the PE files,using SVM to classify the k-length API sequences,and analyzing the risk level of API functions to improve the accuracy of SVM.The experimental results show that proposed method is more efficient than that of which only considers SVM.

Key words: unknown viruses, Win32 API sequence, Support Vector Machine(SVM)