원문정보
보안공학연구지원센터(IJSIA)
International Journal of Security and Its Applications
Vol.5 No.2
2011.04
pp.17-32
피인용수 : 0건 (자료제공 : 네이버학술정보)
초록
영어
This paper describes an ensemble design for cyber security threats detection, which fuses the results from multiple classifiers together to make a final assessment decision. For promoting both speed and accuracy in the detection performance, only some of the features in traffic data are selected for each base classifier. In the kernel of each classifier, we combine Dempster-Shafer theory with k-nearest neighbor technique to solve the uncertainty problems caused by ambiguous and limited intrusion information. In addition, we apply data mining techniques to reduce the number of false alarms. The results indicate that our ensemble approach achieves higher detection rates than that of using a full feature set of classifiers.
목차
Abstract
1. Introduction
2. Related Works
3. Theoretical Framework
3.1 Ensemble Classifier
3.2 k-NN Belief Intrusion Detection Algorithm
3.3 Combination Method
3.4 Data Mining Classifier
4. Experimental Methodology
4.1. The Data Set
4.2. Preprocessing
4.3. Data Selection
5. Experimental Results
6. Conclusions
References
1. Introduction
2. Related Works
3. Theoretical Framework
3.1 Ensemble Classifier
3.2 k-NN Belief Intrusion Detection Algorithm
3.3 Combination Method
3.4 Data Mining Classifier
4. Experimental Methodology
4.1. The Data Set
4.2. Preprocessing
4.3. Data Selection
5. Experimental Results
6. Conclusions
References
저자정보
참고문헌
자료제공 : 네이버학술정보