Control flow-based opcode behavior analysis for Malware detection

被引:60
作者
Ding, Yuxin [1 ]
Dai, Wei [1 ]
Yan, Shengli [1 ]
Zhang, Yumei [2 ]
机构
[1] Shenzhen Univ Town, Harbin Inst Technol, Shenzhen Grad Sch, Shenzhen 518055, Peoples R China
[2] Chinese Acad Sci, State Key Lab Comp Architecture, Inst Comp Technol, Beijing 100864, Peoples R China
关键词
Opcode sequence; Malicious code detection; Control flow graph; Machine learning; Classification; Security;
D O I
10.1016/j.cose.2014.04.003
中图分类号
TP [自动化技术、计算机技术];
学科分类号
0812 ;
摘要
Opcode sequences from decompiled executables have been employed to detect malware. Currently, opcode sequences are extracted using text-based methods, and the limitation of this method is that the extracted opcode sequences cannot represent the true behaviors of an executable. To solve this issue, we present a control flow-based method to extract executable opcode behaviors. The behaviors extracted by this method can fully represent the behavior characteristics of an executable. To verify the efficiency of control flow-based behaviors, we perform a comparative study of the two types of opcode behavior analysis methods. The experimental results indicate that the proposed control flow-based method has a higher overall accuracy and a lower false positive rate. (C) 2014 Elsevier Ltd. All rights reserved.
引用
收藏
页码:65 / 74
页数:10
相关论文
共 26 条
  • [1] Improving support vector machine classifiers by modifying kernel functions
    Amari, S
    Wu, S
    [J]. NEURAL NETWORKS, 1999, 12 (06) : 783 - 789
  • [2] [Anonymous], 1995, P NZ COMPUTER SCI RE
  • [3] [Anonymous], 1996, Proceedings of 1996 IEEE Symposium on Security and Privacy, DOI DOI 10.1109/SECPRI.1996.502675
  • [4] Opcodes as predictor for malware
    Bilar, Daniel
    [J]. INTERNATIONAL JOURNAL OF ELECTRONIC SECURITY AND DIGITAL FORENSICS, 2007, 1 (02) : 156 - 168
  • [5] Cha BR, 2005, IEEE SYMP COMP COMMU, P427
  • [6] Christopher D.Manning., 1999, FDN STAT NATURAL LAN
  • [7] Dash SK, 2005, LECT NOTES COMPUT SC, V3803, P251
  • [8] A fast malware detection algorithm based on objective-oriented association mining
    Ding, Yuxin
    Yuan, Xuebing
    Tang, Ke
    Xiao, Xiao
    Zhang, Yibin
    [J]. COMPUTERS & SECURITY, 2013, 39 : 315 - 324
  • [9] Feature representation and selection in malicious code detection methods based on static system calls
    Ding Yuxin
    Yuan Xuebing
    Zhou Di
    Dong Li
    An Zhanchao
    [J]. COMPUTERS & SECURITY, 2011, 30 (6-7) : 514 - 524
  • [10] Hex-Rays SA, 2009, IDA PROINTRODUCTION