지원사업
학술연구/단체지원/교육 등 연구자 활동을 지속하도록 DBpia가 지원하고 있어요.
커뮤니티
연구자들이 자신의 연구와 전문성을 널리 알리고, 새로운 협력의 기회를 만들 수 있는 네트워킹 공간이에요.
논문 기본 정보
- 자료유형
- 학술저널
- 저자정보
- 발행연도
- 2013.6
- 수록면
- 190 - 198 (9page)
이용수
초록· 키워드
오류제보하기
Automated security management has been a critical but difficult issue in the field of network research. Among various artificial-intelligence techniques, traditional learning techniques based on supervision are not suitable for automated network management, particularly in terms of detecting temporal changes in network intrusion patterns and characteristics, because supervised learning requires a manager. In this regard, unsupervised learning techniques such as the self-organizing map (SOM) are more suitable for automated network management in terms of their configuration, performance, and anomaly detection capability. This paper proposes an automated security management system based on a hierarchical SOM that groups similar data and visualizes their clusters. The proposed system labels maps produced by the SOM based on correlations between features for automated network management. The experimental results for the proposed system based on the 1999 KDD Cup data set indicate that the system shows reasonable misclassification rates and takes 0.5 second to determine whether a behavior is a normal one or an attack.
목차
Abstract
Introduction
Experimental Data Set
SOM-Based Security Management System
Experimental Results
Conclusions
References
참고문헌 (0)
참고문헌 신청이 논문의 저자 정보
이 논문과 함께 이용한 논문
최근 본 자료
댓글(0)
0
UCI(KEPA) : I410-ECN-0101-2015-500-002466493