5G for Future Wireless Networks. First International Conference, 5GWN 2017, Beijing, China, April 21-23, 2017, Proceedings

Research Article

A Novel Intrusion Detection System Based on Advanced Naive Bayesian Classification

Download
327 downloads
  • @INPROCEEDINGS{10.1007/978-3-319-72823-0_53,
        author={Yunpeng Wang and Yuzhou Li and Daxin Tian and Congyu Wang and Wenyang Wang and Rong Hui and Peng Guo and Haijun Zhang},
        title={A Novel Intrusion Detection System Based on Advanced Naive Bayesian Classification},
        proceedings={5G for Future Wireless Networks. First International Conference, 5GWN 2017, Beijing, China, April 21-23, 2017, Proceedings},
        proceedings_a={5GWN},
        year={2018},
        month={1},
        keywords={IDS Information security NBC ReliefF Detection performance KDD’99},
        doi={10.1007/978-3-319-72823-0_53}
    }
    
  • Yunpeng Wang
    Yuzhou Li
    Daxin Tian
    Congyu Wang
    Wenyang Wang
    Rong Hui
    Peng Guo
    Haijun Zhang
    Year: 2018
    A Novel Intrusion Detection System Based on Advanced Naive Bayesian Classification
    5GWN
    Springer
    DOI: 10.1007/978-3-319-72823-0_53
Yunpeng Wang, Yuzhou Li, Daxin Tian,*, Congyu Wang, Wenyang Wang1, Rong Hui1, Peng Guo1, Haijun Zhang2
  • 1: Automotive Engineering Research Institute
  • 2: University of Science and Technology Beijing
*Contact email: dtian@buaa.edu.cn

Abstract

Intrusion Detection System is a pattern recognition task whose aim is to detect and report the occurrence of abnormal or unknown network behaviors in a given network system being monitored. In this paper, we propose a machine learning model, advanced Naive Bayesian Classification (NBC-A) which is based on NBC and ReliefF algorithm, to be used in the novel IDS. We use ReliefF algorithm to give every attribute of network behavior in KDD’99 dataset a weight that reflects the relationship between attributes and final class for better classification results. The novel IDS has a higher True Positive (TP) rate and a lower False Positive (FP) rate in detection performance.