A fuzzy rules based approach for performance anomaly detection

被引：0
作者：
Xu, H [1 ]
You, J [1 ]
Liu, FY [1 ]
机构：
[1] Nanjing Univ Sci & Technol, Comp Sci & Technol Dept, Nanjing 210094, Peoples R China
来源：
2005 IEEE Networking, Sensing and Control Proceedings | 2005年
关键词：
software aging; anomaly detection; negative selection; genetic algorithm;
D O I：
暂无
中图分类号：
TP [自动化技术、计算机技术];
学科分类号：
0812 ;
摘要：
This paper presents a new approach inspired by immunology for system performance anomaly detection, which combines the negative selection algorithm(NSA) and genetic algorithm, generating a set of fuzzy rules that can characterize the normal and the abnormal. NSA serves as a filter to eliminate invalid detectors and reduce search space. Experiments with synthetic and real data sets are performed to show the applicability of the proposed approach.
引用
收藏
页码：44 / 48
页数：5
相关论文
共 13 条
  • [1] [Anonymous], IEEE S SEC PRIV
  • [2] [Anonymous], THESIS PURDUE U
  • [3] Blake C., 1998, UCI REPOSITORY MACHI
  • [4] CAUDELL T, 1993, P PORTL OR, P166
  • [5] Dasgupta D., 1996, Proceedings of the international conference on intelligent systems, P82
  • [6] DAUGPTA D, 2002, IEEE T EVOLUTIONARY, P281
  • [7] Forrest S., 1994, Proceedings of 1994 IEEE Computer Society Symposium on Research in Security and Privacy (Cat. No.94CH3444-7), P202, DOI 10.1109/RISP.1994.296580
  • [8] Kim J, 2001, IEEE C EVOL COMPUTAT, P1244, DOI 10.1109/CEC.2001.934333
  • [9] Kim J., 2001, PROC 3 ANN C GENETIC, P1330
  • [10] Lee W., 1998, P 7 USENIX SEC S SAN
12