원문정보
초록
영어
This paper aimed at the actual situation of the difficult of getting a lot of the training sample of the security computer network system in the distributed intrusion detection. In this paper, we studied how to increase the intrusion detection accuracy in the case of small samples, so that processing, maintenance and deal with the invasion of the network timely. In this paper, we proposed a new intrusion detection method based on improved SVM Co - training. The specific implementation process of the algorithm is presented. Through the simulation experiments based on the actual data showed that the method is effective. Apply this method to a classified computer network system, effectively realized the detection to outside intruders and internal intruder.
목차
1. Introduction
2. Some Definitions on Issues
3. Semi-supervised Learning Algorithm based on Improved SVM
4. The Actual Data Simulation
4.1. The Algorithm Pseudo Code
4.2. Parameter Setting
4.3. Simulation Results
5. Classified Computer Network System based on Distributed Intrusion Detection Technology
6. Conclusion
Acknowledgements
References