Identifying important features for intrusion detection using support vector machines and neural networks

被引：193
|
作者：
Sung, AH [1 ]
Mukkamala, S [1 ]
机构：
[1] New Mexico Inst Min & Technol, Dept Comp Sci, Socorro, NM 87801 USA
来源：
2003 SYMPOSIUM ON APPLICATIONS AND THE INTERNET, PROCEEDINGS | 2003年
关键词：
D O I：
10.1109/SAINT.2003.1183050
中图分类号：
TP [自动化技术、计算机技术];
学科分类号：
0812 ;
摘要：
Intrusion detection is a critical component of secure information systems. This paper addresses the issue of identifying important input features in building an intrusion detection system (IDS). Since elimination of the insignificant and/or useless inputs leads to a simplification of the problem, faster and more accurate detection may result. Feature ranking and selection, therefore, is an important issue in intrusion detection. In this paper we apply the technique of deleting one feature at a time to perform experiments on SVMs and neural networks to rank the importance of input features for the DARPA collected intrusion data. Important features for each of the 5 classes of intrusion patterns in the DARPA data are identified. It is shown that SVM-based and neural network based IDSs using a reduced number of features can deliver enhanced or comparable performance. An IDS for class-specific detection based on five SVMs is proposed.
引用
收藏
页码：209 / 216
页数：8
相关论文
共 50 条
  • [31] Significance analysis of qualitative mammographic features, using linear classifiers, neural networks and support vector machines
    Mavroforakis, M
    Georgiou, H
    Dimitropoulos, N
    Cavouras, D
    Theodoridis, S
    EUROPEAN JOURNAL OF RADIOLOGY, 2005, 54 (01) : 80 - 89
  • [32] Identifying cysteines and histidines in transition-metal-binding sites using support vector machines and neural networks
    Passerini, Andrea
    Punta, Marco
    Ceroni, Alessio
    Rost, Burkhard
    Frasconi, Paolo
    PROTEINS-STRUCTURE FUNCTION AND BIOINFORMATICS, 2006, 65 (02) : 305 - 316
  • [33] Monitoring system security using neural networks and support vector machines
    Mukkamala, S
    Janoski, G
    Sung, A
    HYBRID INFORMATION SYSTEMS, 2002, : 121 - 137
  • [34] Protein fold recognition using neural networks and support vector machines
    Jiang, N
    Wu, WXY
    Mitchell, I
    INTELLIGENT DATA ENGINEERING AND AUTOMATED LEARNING IDEAL 2005, PROCEEDINGS, 2005, 3578 : 462 - 469
  • [35] Texture inspection for defects using neural networks and support vector machines
    Kumar, A
    Shen, HC
    2002 INTERNATIONAL CONFERENCE ON IMAGE PROCESSING, VOL III, PROCEEDINGS, 2002, : 353 - 356
  • [36] Biased support vector machines and kernel methods for intrusion detection
    Yendrapalli, K.
    Mukkamala, S.
    Sung, A. H.
    Ribeiro, B.
    WORLD CONGRESS ON ENGINEERING 2007, VOLS 1 AND 2, 2007, : 321 - +
  • [37] Network-based intrusion detection with support vector machines
    Kim, DS
    Park, JS
    INFORMATION NETWORKING: NETWORKING TECHNOLOGIES FOR ENHANCED INTERNET SERVICES, 2003, 2662 : 747 - 756
  • [38] Application of weighted support vector machines to network intrusion detection
    Jia, YS
    Jia, CY
    Qi, HW
    SHAPING BUSINESS STRATEGY IN A NETWORKED WORLD, VOLS 1 AND 2, PROCEEDINGS, 2004, : 1025 - 1029
  • [39] An eye detection method based on convolutional neural networks and support vector machines
    Yu, Mingxin
    Tang, Xiaoying
    Lin, Yingzi
    Schmidt, David
    Wang, Xiangzhou
    Guo, Yikang
    Liang, Bo
    INTELLIGENT DATA ANALYSIS, 2018, 22 (02) : 345 - 362
  • [40] Freight Car Roller Bearing Fault Detection Using Artificial Neural Networks and Support Vector Machines
    Maraini, Daniel
    Nataraj, C.
    VIBRATION ENGINEERING AND TECHNOLOGY OF MACHINERY, 2015, 23 : 663 - +
12345