3rd International ICST Conference on Security and Privacy in Communication Networks

Research Article

Intrusion Detection Technology based on CEGA-SVM

  • @INPROCEEDINGS{10.1109/SECCOM.2007.4550339,
        author={Yuxin Wei and Muqing Wu},
        title={Intrusion Detection Technology based on CEGA-SVM},
        proceedings={3rd International ICST Conference on Security and Privacy in Communication Networks},
        publisher={IEEE},
        proceedings_a={SECURECOMM},
        year={2008},
        month={6},
        keywords={conditional entropy  genetic algorithm  intrusion detection  optimal feature subset  support vector machine},
        doi={10.1109/SECCOM.2007.4550339}
    }
    
  • Yuxin Wei
    Muqing Wu
    Year: 2008
    Intrusion Detection Technology based on CEGA-SVM
    SECURECOMM
    IEEE
    DOI: 10.1109/SECCOM.2007.4550339
Yuxin Wei1,*, Muqing Wu1,*
  • 1: Institute of Communication Networks Integrated Technique BUPT, Beijing, China
*Contact email: weiyuxin@gmail.com, wumuqing@bupt.edu.cn

Abstract

In order to improve the classification accuracy and reduce the detection time, the optimization of feature extraction and SVM training model is combined together. In the procedure of feature extraction using CEGA with adaptive crossover and mutation, fitness of the individual is evaluated by the correct classification rate and conditional entropy. The optimization of SVM training model is processed at the same time with the feature extraction in order to find the best combination of optimal feature subset with the SVM training model. Results of the experiment using KDD CUP99 data sets demonstrate that applying CEGA-SVM can be an effective way for feature extraction and intrusion detection.