[1]翟宏群,冯茂岩.一种改进的变阈值阴性选择免疫算法[J].南京师范大学学报(工程技术版),2011,11(03):078-82.
　Zhai Hongqun,Feng Maoyan.An Improved Adjustable Threshold Intrusion Detection Negative Selection Immune Algorithm[J].Journal of Nanjing Normal University(Engineering and Technology),2011,11(03):078-82.
点击复制

一种改进的变阈值阴性选择免疫算法
分享到：

南京师范大学学报（工程技术版）[ISSN:1006-6977/CN:61-1281/TN]

卷:
11卷
期数:
2011年03期
页码:
078-82
栏目:
出版日期:
2011-11-30

文章信息/Info

Title:
An Improved Adjustable Threshold Intrusion Detection Negative Selection Immune Algorithm
作者:
翟宏群;冯茂岩;
江苏海事职业技术学院信息工程系，江苏南京211170
Author(s):
Zhai Hongqun; Feng Maoyan
Information Department,Jiangsu Maritime Institute,Nanjing 211170,China
关键词:
阴性选择; 优先搜索; 检测元集; 黑洞
Keywords:
negative selection; optimal search; detector set; black holes
分类号:
TP393.08
摘要:
成功确定一个最有效检测元集是提高免疫阴性选择算法性能的关键步骤,它直接影响到系统的效率和准确度.利用模糊思想,提出了一种生成最有效检测元集的变阈值阴性选择免疫算法.采用最优搜索原理,有效提高了待检测的检测元成为成熟检测元的概率;匹配阈值可变,可大幅降低黑洞数量.仿真结果表明,该算法与原算法相比,具有较高的检测率和较少的黑洞数量,算法具有较强的鲁棒性.
Abstract:
Success in confirming the most effective detector set is a key step to improve negative selection algorithm capability， which has a direct affect on efficiency and veracity of system． Fuzzy idea was used to put forward an adjustable threshold negative selection immune algorithm of creating the most effective detector set． The rate of mature detector activated can be improved effectively based on optimal search theory and the number of black holes can be reduced clearly through adjusting matching threshold in this algorithm． The simulation results indicate that this new algorithm in comparison with the original algorithm，is of higher detection efficiency and lower detection holes number，and thus the algorithm has better robustness．

参考文献/References:

［1］Hofmeyr S，Forrest S． Immunity by design: An artificial immune system［C］/ / Wolfgan B，Jason M D，et al，eds． Proc of the Genetic and Evolutionary Computation Conf． San Francisco: Morgan Kaufman Publishers，1999．
［2］De Castro L N，Timmis J． Artificial Immune Systems: A New Computational Intelligence Approach［M］． Heidelberg: Springer- Verlag，2002．
［3］Kelsey J，Hender S B，Seymour R M． A stochastic model of the interleukin ( IL) 21 B network ［C］/ /Proceeding of the 7th International Conference on Artificial Immune Systems． Phuket: Springer，2008: 1 211．
［4］Andrews P S，Timm I S J． Adaptable lymphocytes for artificial immune systems［C］/ /Proceeding of the 7th International Conference on Artificial Immune Systems． Phuket: Springer，2008: 3 762 386．
［5］张宇． 人工免疫系统中阴性选择算法的研究［D］． 杭州: 浙江大学电气工程学院，2007． Zhang Yu． Research on negative selection algorithm of artificial immune system［D］． Hangzhou: School of Electrical Engineering， Zhejiang University，2007． ( in Chinese)
［6］周建国． 网络入侵检测的免疫学建模及其仿真研究［D］． 北京: 北京航空航天大学计算机学院，2002． Zhou Jianguo． Immunological moding of network intrusion detection ＆ its simulate research ［D］． Beijing: School of Computer， Beijing University of Aeronautics and Astronautics，2002． ( in Chinese)
［7］Hofmeyr S A． An immunological model of distributed detection and its application to computer security［D］． Albuquerque， NM: Computer Science Department，University of New Mexico，1999．
［8］D’haesseleer P． Further efficient algorithms for generating antibody string，Technical Report CS95-03［R］． New Mexico: The University of New Mexico，1995．

备注/Memo

备注/Memo:
基金项目: 江苏省“网络与信息安全”重点实验室课题( BM2003201) ．通讯联系人: 翟宏群，讲师，研究方向: 计算机应用技术、网络安全． E-mail: hqzhai@126． Com
更新日期/Last Update: 2013-03-21